# REAA Standard Library — full catalog > 312 MIT-licensed TypeScript packages for production AI agents. > 302 published to npm, 10 pending across 41 repos. > Authored and maintained by REAA Technologies. > > Grouped by category (display order), then repo (a–z), then package slug (a–z). # Testing & Security > 50 packages — Chaos testing, prompt injection benches, tool-use firewalls. ## @reaatech/agent-auth-proxy-client **Category:** Testing & Security · **Repo:** agent-auth-proxy · **Status:** published v2.0.0 Two typed HTTP clients for the agent-auth-proxy server: `AgentClient` exchanges an API key for a JWT and makes proxied requests to third-party APIs on behalf of a user, while `AdminClient` manages users, agents, grants, and tokens. Both decode server errors into typed error classes (`AuthError`, `ScopeError`, `ValidationError`, `UpstreamError`, `AppError`). - npm: https://www.npmjs.com/package/@reaatech/agent-auth-proxy-client - detail: https://reaatech.com/products/testing-security/agent-auth-proxy/packages/agent-auth-proxy-client - repo: https://github.com/reaatech/agent-auth-proxy - tags: agent-auth-proxy, client, sdk, oauth2 ## @reaatech/agent-auth-proxy-core **Category:** Testing & Security · **Repo:** agent-auth-proxy · **Status:** published v2.0.0 Shared Zod schemas, error classes, and TypeScript types for OAuth2 proxy request validation, scope management, and error handling, exported as framework-agnostic primitives that only depend on `zod`. - npm: https://www.npmjs.com/package/@reaatech/agent-auth-proxy-core - detail: https://reaatech.com/products/testing-security/agent-auth-proxy/packages/agent-auth-proxy-core - repo: https://github.com/reaatech/agent-auth-proxy - tags: agent-auth-proxy, types, zod, schemas ## @reaatech/agent-auth-proxy-server **Category:** Testing & Security · **Repo:** agent-auth-proxy · **Status:** published v2.0.0 Fastify plugin and CLI that implements an identity-aware proxy server for agent-to-service communication, handling API key auth, OAuth2 with PKCE, JWT issuance, scope enforcement, credential injection, and audit logging. Exports `buildApp()` and `start()` functions, requires a PostgreSQL database and pairs with `@reaatech/agent-auth-proxy-core` for shared schemas. - npm: https://www.npmjs.com/package/@reaatech/agent-auth-proxy-server - detail: https://reaatech.com/products/testing-security/agent-auth-proxy/packages/agent-auth-proxy-server - repo: https://github.com/reaatech/agent-auth-proxy - tags: proxy, auth, oauth2, api, agent, identity, security, fastify ## @reaatech/agent-chaos-adapters **Category:** Testing & Security · **Repo:** agent-chaos · **Status:** pending npm Framework adapters for injecting fault-tolerance testing into LangChain, LlamaIndex, Vercel AI SDK, or any custom agent with a tool-call interface, using a shared interceptor pattern that wraps tools without modifying agent code. Each adapter exports a framework-specific wrapper (e.g., a tool wrapper for LangChain, a tool spec wrapper for LlamaIndex) that pairs with the `@reaatech/agent-chaos-core` engine at runtime. - npm: pending — package not yet published as @reaatech/agent-chaos-adapters - detail: https://reaatech.com/products/testing-security/agent-chaos/packages/agent-chaos-adapters - repo: https://github.com/reaatech/agent-chaos ## @reaatech/agent-chaos-cli **Category:** Testing & Security · **Repo:** agent-chaos · **Status:** published v0.1.0 A CLI that validates, generates, and runs chaos engineering scenarios for AI agents, providing `init`, `generate`, `validate`, and `run` commands for managing fault-injection test scenarios defined in YAML or JSON. - npm: https://www.npmjs.com/package/@reaatech/agent-chaos-cli - detail: https://reaatech.com/products/testing-security/agent-chaos/packages/agent-chaos-cli - repo: https://github.com/reaatech/agent-chaos - tags: chaos, chaos-engineering, fault-injection, cli, agent ## @reaatech/agent-chaos-core **Category:** Testing & Security · **Repo:** agent-chaos · **Status:** published v0.1.0 Middleware-based fault injection engine for agent systems that intercepts tool calls and injects latency, timeout, malformed output, token exhaustion, and other failure modes via a single `engine.intercept()` call, with scenario-driven YAML/JSON configuration, probability-based fault selection, and seeded randomness for reproducible testing. - npm: https://www.npmjs.com/package/@reaatech/agent-chaos-core - detail: https://reaatech.com/products/testing-security/agent-chaos/packages/agent-chaos-core - repo: https://github.com/reaatech/agent-chaos - tags: chaos, chaos-engineering, fault-injection, agent, llm, resilience, testing ## @reaatech/agent-chaos-e2e **Category:** Testing & Security · **Repo:** agent-chaos · **Status:** pending npm End-to-end test suite that validates the full agent-chaos pipeline—scenario loading, schema validation, fault injection, engine event recording, CLI execution, and cross-package integration—against mock agent implementations. - npm: pending — package not yet published as @reaatech/agent-chaos-e2e - detail: https://reaatech.com/products/testing-security/agent-chaos/packages/agent-chaos-e2e - repo: https://github.com/reaatech/agent-chaos ## @reaatech/agent-chaos-observability **Category:** Testing & Security · **Repo:** agent-chaos · **Status:** pending npm Structured logging, metrics collection, OpenTelemetry tracing, and report generation for chaos engineering experiments, exposed as a set of classes (`MetricsCollector`, `Tracer`, `ReportGenerator`) that consume events from `@reaatech/agent-chaos-core`. - npm: pending — package not yet published as @reaatech/agent-chaos-observability - detail: https://reaatech.com/products/testing-security/agent-chaos/packages/agent-chaos-observability - repo: https://github.com/reaatech/agent-chaos ## @reaatech/agent-chaos-scenarios **Category:** Testing & Security · **Repo:** agent-chaos · **Status:** published v0.1.0 A scenario loader and validator for the agent-chaos fault injection toolkit that parses YAML and JSON scenario files, validates them against a JSON Schema, supports composition via `extends` with circular reference detection, and provides hot-reloading via file watching. Exports `ScenarioLoader` and `SchemaValidator` classes, plus a `createScenarioLoader` factory function; depends on `yaml`, `ajv`, and `ajv-formats` at runtime. - npm: https://www.npmjs.com/package/@reaatech/agent-chaos-scenarios - detail: https://reaatech.com/products/testing-security/agent-chaos/packages/agent-chaos-scenarios - repo: https://github.com/reaatech/agent-chaos - tags: chaos, chaos-engineering, fault-injection, scenarios, yaml, agent ## @reaatech/guardrail-chain **Category:** Testing & Security · **Repo:** guardrail-chain · **Status:** published v0.1.0 Core types, chain orchestration, budget management, and utilities for the Guardrail Chain framework, providing the `Guardrail` interface and `GuardrailChain` orchestrator that every guardrail implementation must satisfy. - npm: https://www.npmjs.com/package/@reaatech/guardrail-chain - detail: https://reaatech.com/products/testing-security/guardrail-chain/packages/guardrail-chain - repo: https://github.com/reaatech/guardrail-chain - tags: guardrail, llm, ai, pipeline, safety, moderation ## @reaatech/guardrail-chain-config **Category:** Testing & Security · **Repo:** guardrail-chain · **Status:** published v0.1.0 Loads and validates Guardrail Chain configuration from JSON, YAML, and environment variables, providing functions like `loadConfig`, `validateConfig`, and `validateConfigSafe` that deep-merge sources and validate against a Zod schema. - npm: https://www.npmjs.com/package/@reaatech/guardrail-chain-config - detail: https://reaatech.com/products/testing-security/guardrail-chain/packages/guardrail-chain-config - repo: https://github.com/reaatech/guardrail-chain - tags: config, configuration, validation, guardrail ## @reaatech/guardrail-chain-guardrails **Category:** Testing & Security · **Repo:** guardrail-chain · **Status:** published v0.1.0 Thirteen built-in guardrail implementations for the Guardrail Chain framework, covering input validation, output filtering, and result caching. Each guardrail is a class implementing the `Guardrail` interface from `@reaatech/guardrail-chain`, designed to be composed into a chain with budget-aware scheduling. - npm: https://www.npmjs.com/package/@reaatech/guardrail-chain-guardrails - detail: https://reaatech.com/products/testing-security/guardrail-chain/packages/guardrail-chain-guardrails - repo: https://github.com/reaatech/guardrail-chain - tags: guardrail, llm, ai, pii, prompt-injection, toxicity, moderation ## @reaatech/guardrail-chain-observability **Category:** Testing & Security · **Repo:** guardrail-chain · **Status:** published v0.1.0 Pluggable observability interfaces for the Guardrail Chain framework providing structured logging, metrics collection, and distributed tracing via module-level singletons (`getLogger`/`setLogger`, `getMetrics`/`setMetrics`, `getTracer`/`setTracer`). Ships with no-op defaults and a `ConsoleLogger` for development, with zero runtime dependencies. - npm: https://www.npmjs.com/package/@reaatech/guardrail-chain-observability - detail: https://reaatech.com/products/testing-security/guardrail-chain/packages/guardrail-chain-observability - repo: https://github.com/reaatech/guardrail-chain - tags: observability, logging, metrics, tracing, guardrail ## @reaatech/mcp-contract-cli **Category:** Testing & Security · **Repo:** mcp-contract-kit · **Status:** published v0.2.1 CLI tool and programmatic API for running conformance tests against MCP servers, covering protocol, registry, routing, security, and performance validators. Exports `runTests`, `validateRegistry`, and `generateReport` functions, plus a `mcp-contract-kit` CLI binary. - npm: https://www.npmjs.com/package/@reaatech/mcp-contract-cli - detail: https://reaatech.com/products/testing-security/mcp-contract-kit/packages/mcp-contract-cli - repo: https://github.com/reaatech/mcp-contract-kit ## @reaatech/mcp-contract-client **Category:** Testing & Security · **Repo:** mcp-contract-kit · **Status:** published v0.2.0 A factory function (`createMCPClient`) and class (`MCPHttpClient`) for connecting to Model Context Protocol servers over HTTP, providing tool discovery, tool invocation, JSON-RPC 2.0 request/response, SSE streaming, and automatic retry with configurable backoff. - npm: https://www.npmjs.com/package/@reaatech/mcp-contract-client - detail: https://reaatech.com/products/testing-security/mcp-contract-kit/packages/mcp-contract-client - repo: https://github.com/reaatech/mcp-contract-kit ## @reaatech/mcp-contract-core **Category:** Testing & Security · **Repo:** mcp-contract-kit · **Status:** published v0.1.1 Core domain types, JSON-RPC 2.0 schemas, and shared utilities for MCP contract validation, providing enums (`Severity`, `TestCategory`, `TestSuite`), result interfaces (`TestResult`, `TestReport`), validator contracts, MCP client types, Zod schemas for runtime validation, and helper functions (UUID generation, retry with backoff, URL validation, statistics, redaction). - npm: https://www.npmjs.com/package/@reaatech/mcp-contract-core - detail: https://reaatech.com/products/testing-security/mcp-contract-kit/packages/mcp-contract-core - repo: https://github.com/reaatech/mcp-contract-kit ## @reaatech/mcp-contract-observability **Category:** Testing & Security · **Repo:** mcp-contract-kit · **Status:** published v0.1.1 A pino-based structured logger, in-memory metrics collector, and W3C trace context propagator for MCP contract validation. Exports a logger singleton with automatic PII redaction, a `metrics` object with counters and duration histograms, and `startSpan`/`endSpan`/`withSpan` helpers for creating and propagating trace contexts via W3C traceparent headers. - npm: https://www.npmjs.com/package/@reaatech/mcp-contract-observability - detail: https://reaatech.com/products/testing-security/mcp-contract-kit/packages/mcp-contract-observability - repo: https://github.com/reaatech/mcp-contract-kit ## @reaatech/mcp-contract-reporters **Category:** Testing & Security · **Repo:** mcp-contract-kit · **Status:** published v0.1.1 A set of reporter functions that consume `TestReport` objects from `@reaatech/mcp-contract-core` and render them as colored console output, JSON, GitHub-flavored Markdown, or a self-contained HTML dashboard. - npm: https://www.npmjs.com/package/@reaatech/mcp-contract-reporters - detail: https://reaatech.com/products/testing-security/mcp-contract-kit/packages/mcp-contract-reporters - repo: https://github.com/reaatech/mcp-contract-kit ## @reaatech/mcp-contract-validators **Category:** Testing & Security · **Repo:** mcp-contract-kit · **Status:** published v0.1.2 A set of conformance validators for MCP servers that checks protocol compliance (JSON-RPC 2.0), registry configuration, routing contracts, security posture, and performance baselines. Exports validator functions that take a client context and return pass/fail results with diagnostic messages. - npm: https://www.npmjs.com/package/@reaatech/mcp-contract-validators - detail: https://reaatech.com/products/testing-security/mcp-contract-kit/packages/mcp-contract-validators - repo: https://github.com/reaatech/mcp-contract-kit ## @reaatech/mcp-load-test-analysis **Category:** Testing & Security · **Repo:** mcp-load-test · **Status:** published v0.1.0 Provides breaking point detection and performance grading for MCP load test reports. Exports `BreakingPointDetector` (a class that monitors error rates and latency against configurable thresholds during a test, tracking when the server degrades and recovers) and `Grader` (a class that assigns A–F letter grades for latency, concurrency, and error rate, and generates actionable recommendations). Designed to consume `LoadTestReport` objects from `@reaatech/mcp-load-test-core`. - npm: https://www.npmjs.com/package/@reaatech/mcp-load-test-analysis - detail: https://reaatech.com/products/testing-security/mcp-load-test/packages/mcp-load-test-analysis - repo: https://github.com/reaatech/mcp-load-test ## @reaatech/mcp-load-test-cli **Category:** Testing & Security · **Repo:** mcp-load-test · **Status:** published v0.1.0 A CLI that runs load, ramp, soak, and spike tests against MCP servers, outputting results to the console, Markdown, or JSON. Built on Commander.js, it accepts YAML or JSON config files and supports auto-detection of stdio, SSE, or HTTP transport. - npm: https://www.npmjs.com/package/@reaatech/mcp-load-test-cli - detail: https://reaatech.com/products/testing-security/mcp-load-test/packages/mcp-load-test-cli - repo: https://github.com/reaatech/mcp-load-test ## @reaatech/mcp-load-test-client **Category:** Testing & Security · **Repo:** mcp-load-test · **Status:** published v0.1.0 A session-scoped MCP transport client that auto-negotiates across stdio, SSE, and StreamableHTTP, providing `connect()`, `disconnect()`, `callTool()`, and `listTools()` methods for concurrent load-test sessions. - npm: https://www.npmjs.com/package/@reaatech/mcp-load-test-client - detail: https://reaatech.com/products/testing-security/mcp-load-test/packages/mcp-load-test-client - repo: https://github.com/reaatech/mcp-load-test ## @reaatech/mcp-load-test-core **Category:** Testing & Security · **Repo:** mcp-load-test · **Status:** published v0.1.0 Shared TypeScript types, Zod schemas, utility functions (percentile calculation, retry with backoff, URL validation), and a pre-configured Pino logger that serve as the single source of truth for all domain shapes in the `@reaatech/mcp-load-test-*` ecosystem. - npm: https://www.npmjs.com/package/@reaatech/mcp-load-test-core - detail: https://reaatech.com/products/testing-security/mcp-load-test/packages/mcp-load-test-core - repo: https://github.com/reaatech/mcp-load-test ## @reaatech/mcp-load-test-engine **Category:** Testing & Security · **Repo:** mcp-load-test · **Status:** published v0.1.0 A `LoadEngine` class that orchestrates MCP server load tests by managing a dynamic session pool, executing weighted-random tool call patterns, and producing a `LoadTestReport` with metrics, breaking point detection, and an auto-generated grade. - npm: https://www.npmjs.com/package/@reaatech/mcp-load-test-engine - detail: https://reaatech.com/products/testing-security/mcp-load-test/packages/mcp-load-test-engine - repo: https://github.com/reaatech/mcp-load-test ## @reaatech/mcp-load-test-metrics **Category:** Testing & Security · **Repo:** mcp-load-test · **Status:** published v0.1.0 A latency histogram, throughput collector, and error tracker for MCP load testing, exposed as a `MetricsCollector` class that records per-tool percentile distributions, rolling-window error rates, and peak RPS from raw request records. - npm: https://www.npmjs.com/package/@reaatech/mcp-load-test-metrics - detail: https://reaatech.com/products/testing-security/mcp-load-test/packages/mcp-load-test-metrics - repo: https://github.com/reaatech/mcp-load-test ## @reaatech/mcp-load-test-patterns **Category:** Testing & Security · **Repo:** mcp-load-test · **Status:** published v0.1.0 A pattern execution engine and three built-in tool-call sequences (`EXPLORE_THEN_ACT`, `READ_THEN_WRITE`, `MULTI_STEP_WORKFLOW`) for load testing MCP servers, provided as a `PatternExecutor` class that resolves template variables, applies configurable think-time delays, and categorizes errors. - npm: https://www.npmjs.com/package/@reaatech/mcp-load-test-patterns - detail: https://reaatech.com/products/testing-security/mcp-load-test/packages/mcp-load-test-patterns - repo: https://github.com/reaatech/mcp-load-test ## @reaatech/mcp-load-test-profiles **Category:** Testing & Security · **Repo:** mcp-load-test · **Status:** published v0.1.0 Async generator functions that yield `{ concurrency, phase }` tuples at 1-second intervals for four load-testing profiles (ramp, soak, spike, and custom curve), designed to drive an MCP load-test engine's session pool. - npm: https://www.npmjs.com/package/@reaatech/mcp-load-test-profiles - detail: https://reaatech.com/products/testing-security/mcp-load-test/packages/mcp-load-test-profiles - repo: https://github.com/reaatech/mcp-load-test ## @reaatech/mcp-load-test-reporters **Category:** Testing & Security · **Repo:** mcp-load-test · **Status:** published v0.1.0 Console, markdown, and JSON output formatters for MCP load test reports. Each reporter is a class with a `format(report: LoadTestReport): string` method, producing either ANSI-colored terminal output, GitHub-flavored markdown, or pretty-printed JSON. - npm: https://www.npmjs.com/package/@reaatech/mcp-load-test-reporters - detail: https://reaatech.com/products/testing-security/mcp-load-test/packages/mcp-load-test-reporters - repo: https://github.com/reaatech/mcp-load-test ## @reaatech/mcp-server-doctor-cli **Category:** Testing & Security · **Repo:** mcp-server-doctor · **Status:** published v1.0.0 A CLI that runs a full diagnostic suite against an MCP server endpoint, compares reports to detect regressions, or continuously monitors an endpoint for grade drops. It ships the `doctor` and `mcp-server-doctor` binaries. - npm: https://www.npmjs.com/package/@reaatech/mcp-server-doctor-cli - detail: https://reaatech.com/products/testing-security/mcp-server-doctor/packages/mcp-server-doctor-cli - repo: https://github.com/reaatech/mcp-server-doctor ## @reaatech/mcp-server-doctor-client **Category:** Testing & Security · **Repo:** mcp-server-doctor · **Status:** published v1.0.0 An MCP transport client that auto-negotiates between stdio, SSE, and streamable HTTP transports, providing a `createDoctorClient` factory function that returns an `MCPClient` interface with `connect`, `disconnect`, `listTools`, `callTool`, `sendRequest`, `getSessionId`, and `getServerInfo` methods. - npm: https://www.npmjs.com/package/@reaatech/mcp-server-doctor-client - detail: https://reaatech.com/products/testing-security/mcp-server-doctor/packages/mcp-server-doctor-client - repo: https://github.com/reaatech/mcp-server-doctor ## @reaatech/mcp-server-doctor-core **Category:** Testing & Security · **Repo:** mcp-server-doctor · **Status:** published v1.0.0 Shared domain types, Zod schemas, grading benchmarks, and utility functions for the `@reaatech/mcp-server-doctor-*` diagnostic ecosystem, exporting TypeScript types (`DiagnosticReport`, `CheckResult`, `LatencyMetrics`), enums (`CheckCategory`, `Severity`, `Grade`), grading functions (`gradeCompliance`, `gradeLatency`, `computeOverallGrade`), and helpers (`generateUUID`, `percentile`, `calculateStats`). - npm: https://www.npmjs.com/package/@reaatech/mcp-server-doctor-core - detail: https://reaatech.com/products/testing-security/mcp-server-doctor/packages/mcp-server-doctor-core - repo: https://github.com/reaatech/mcp-server-doctor ## @reaatech/mcp-server-doctor-engine **Category:** Testing & Security · **Repo:** mcp-server-doctor · **Status:** published v1.0.0 A diagnostic engine that runs 8 health checks against an MCP server, computes a composite A–F grade, and produces a structured `DiagnosticReport`. Exports a `DiagnosticEngine` class with a `run()` method, plus individual check classes that implement a `validate(client, context)` interface. - npm: https://www.npmjs.com/package/@reaatech/mcp-server-doctor-engine - detail: https://reaatech.com/products/testing-security/mcp-server-doctor/packages/mcp-server-doctor-engine - repo: https://github.com/reaatech/mcp-server-doctor ## @reaatech/mcp-server-doctor-observability **Category:** Testing & Security · **Repo:** mcp-server-doctor · **Status:** published v1.0.0 A Pino-based structured logger and OpenTelemetry metrics/tracing module for MCP server diagnostics, exporting a singleton `logger`, metric recording functions (`recordCheck`, `recordLatency`, `recordGrade`), and a `startSpan` tracer. - npm: https://www.npmjs.com/package/@reaatech/mcp-server-doctor-observability - detail: https://reaatech.com/products/testing-security/mcp-server-doctor/packages/mcp-server-doctor-observability - repo: https://github.com/reaatech/mcp-server-doctor ## @reaatech/mcp-server-doctor-reporters **Category:** Testing & Security · **Repo:** mcp-server-doctor · **Status:** published v1.0.0 A single dispatch function `formatReport(report, format)` that formats a `DiagnosticReport` object into console, JSON, markdown, or HTML output, with individual formatters also exported for direct use. - npm: https://www.npmjs.com/package/@reaatech/mcp-server-doctor-reporters - detail: https://reaatech.com/products/testing-security/mcp-server-doctor/packages/mcp-server-doctor-reporters - repo: https://github.com/reaatech/mcp-server-doctor ## @reaatech/pi-bench-adapters **Category:** Testing & Security · **Repo:** prompt-injection-bench · **Status:** published v1.0.1 A collection of pluggable defense adapters for prompt injection detection, providing a standard `DefenseAdapter` interface with `detect()` and `sanitize()` methods across 8 built-in implementations (Rebuff, Lakera Guard, LLM Guard, Garak, OpenAI/Azure/Anthropic/Cohere Moderation, and Custom HTTP). Each adapter extends `BaseAdapter` which handles input validation, SSRF protection, rate limiting, and injection pattern detection. - npm: https://www.npmjs.com/package/@reaatech/pi-bench-adapters - detail: https://reaatech.com/products/testing-security/prompt-injection-bench/packages/pi-bench-adapters - repo: https://github.com/reaatech/prompt-injection-bench ## @reaatech/pi-bench-core **Category:** Testing & Security · **Repo:** prompt-injection-bench · **Status:** published v1.0.1 Canonical TypeScript types, Zod schemas, and attack taxonomy for the prompt-injection-bench benchmarking suite. Exports 18 domain types, 16 Zod schemas for runtime validation, and an 8-category attack taxonomy with weights and severity levels, with zero runtime dependencies beyond Zod. - npm: https://www.npmjs.com/package/@reaatech/pi-bench-core - detail: https://reaatech.com/products/testing-security/prompt-injection-bench/packages/pi-bench-core - repo: https://github.com/reaatech/prompt-injection-bench ## @reaatech/pi-bench-corpus **Category:** Testing & Security · **Repo:** prompt-injection-bench · **Status:** published v1.0.1 A corpus builder, validator, and variant generation engine for prompt-injection-bench that produces balanced injection samples from YAML templates using synonym replacement, Unicode homoglyphs, and other obfuscation strategies. Exports factory functions (`createCorpusBuilder`, `createCorpusValidator`) and a `generateDefaultCorpus` function. - npm: https://www.npmjs.com/package/@reaatech/pi-bench-corpus - detail: https://reaatech.com/products/testing-security/prompt-injection-bench/packages/pi-bench-corpus - repo: https://github.com/reaatech/prompt-injection-bench ## @reaatech/pi-bench-leaderboard **Category:** Testing & Security · **Repo:** prompt-injection-bench · **Status:** published v1.0.1 A leaderboard manager for prompt-injection-bench that ranks defenses by composite score into S/A/B/C/D tiers, with JSON file persistence and pairwise comparison. Exports a `createLeaderboardManager` factory function and standalone `loadLeaderboardEntries`/`saveLeaderboardEntries` utilities. - npm: https://www.npmjs.com/package/@reaatech/pi-bench-leaderboard - detail: https://reaatech.com/products/testing-security/prompt-injection-bench/packages/pi-bench-leaderboard - repo: https://github.com/reaatech/prompt-injection-bench ## @reaatech/pi-bench-mcp-server **Category:** Testing & Security · **Repo:** prompt-injection-bench · **Status:** published v1.0.1 An MCP server that exposes four tools (`run_benchmark`, `compare_defenses`, `generate_report`, `submit_results`) for running prompt injection benchmarks against defenses, comparing results, and generating reports. It provides a `createMCPServer` factory function and a `normalizeReportData` utility for standardizing benchmark results across different formats. - npm: https://www.npmjs.com/package/@reaatech/pi-bench-mcp-server - detail: https://reaatech.com/products/testing-security/prompt-injection-bench/packages/pi-bench-mcp-server - repo: https://github.com/reaatech/prompt-injection-bench ## @reaatech/pi-bench-observability **Category:** Testing & Security · **Repo:** prompt-injection-bench · **Status:** published v1.0.1 A structured logging, OpenTelemetry-compatible metrics, and span-based tracing toolkit for benchmark operations, built on Pino v10 and the OpenTelemetry SDK. It provides `createLogger()`, `createMetricsCollector()`, and `createTracingManager()` factory functions, plus global singleton accessors (`getGlobalLogger()`, `getGlobalTracer()`, `getGlobalMetrics()`) for zero-config usage. - npm: https://www.npmjs.com/package/@reaatech/pi-bench-observability - detail: https://reaatech.com/products/testing-security/prompt-injection-bench/packages/pi-bench-observability - repo: https://github.com/reaatech/prompt-injection-bench ## @reaatech/pi-bench-runner **Category:** Testing & Security · **Repo:** prompt-injection-bench · **Status:** published v1.0.1 A benchmark execution engine that runs prompt injection attacks against defense adapters in parallel with configurable timeouts, progress reporting, and PII-safe result collection. Exports factory functions (`createBenchmarkEngine`, `createAttackExecutor`, `createDefenseEvaluator`) and requires a `DefenseAdapter` and attack corpus (e.g., from `@reaatech/pi-bench-adapters` and `@reaatech/pi-bench-corpus`). - npm: https://www.npmjs.com/package/@reaatech/pi-bench-runner - detail: https://reaatech.com/products/testing-security/prompt-injection-bench/packages/pi-bench-runner - repo: https://github.com/reaatech/prompt-injection-bench ## @reaatech/pi-bench-scoring **Category:** Testing & Security · **Repo:** prompt-injection-bench · **Status:** published v1.0.1 Computes weighted defense scores, confidence intervals, effect sizes, and statistical comparisons (z-test, chi-square, ANOVA) for prompt-injection benchmark results, exporting functions like `calculateDefenseScore`, `compareMetrics`, and `createStatisticalTests`. - npm: https://www.npmjs.com/package/@reaatech/pi-bench-scoring - detail: https://reaatech.com/products/testing-security/prompt-injection-bench/packages/pi-bench-scoring - repo: https://github.com/reaatech/prompt-injection-bench ## prompt-injection-bench **Category:** Testing & Security · **Repo:** prompt-injection-bench · **Status:** published v1.0.1 A CLI and library for benchmarking LLM prompt-injection defenses against standardized attack corpora. Exports a `createBenchmarkEngine` function and CLI with subcommands (`benchmark`, `attack`, `compare`, `corpus`, `leaderboard`, `report`) that work with defense adapters for services like Rebuff, Lakera, and OpenAI Moderation. - npm: https://www.npmjs.com/package/prompt-injection-bench - detail: https://reaatech.com/products/testing-security/prompt-injection-bench/packages/prompt-injection-bench - repo: https://github.com/reaatech/prompt-injection-bench ## tool-use-firewall **Category:** Testing & Security · **Repo:** tool-use-firewall · **Status:** published v0.2.0 A CLI and programmatic proxy server that intercepts every tool call from an AI agent to an MCP server, validating each call against a policy file before forwarding it upstream. Exports an `MCPProxyServer` class for programmatic use and a `tool-use-firewall` binary that accepts `--config` and `--upstream` arguments. - npm: https://www.npmjs.com/package/tool-use-firewall - detail: https://reaatech.com/products/testing-security/tool-use-firewall/packages/tool-use-firewall - repo: https://github.com/reaatech/tool-use-firewall - tags: mcp, firewall, ai-agent, policy, security, proxy, cli ## @reaatech/tool-use-firewall-approvals **Category:** Testing & Security · **Repo:** tool-use-firewall · **Status:** published v0.2.0 A human-in-the-loop approval workflow engine for tool-use-firewall that provides an `ApprovalWorkflow` class for managing multi-level approval chains with timeouts, plus Express-based REST API, CLI prompts, and webhook/Slack/Discord notification approvers. - npm: https://www.npmjs.com/package/@reaatech/tool-use-firewall-approvals - detail: https://reaatech.com/products/testing-security/tool-use-firewall/packages/tool-use-firewall-approvals - repo: https://github.com/reaatech/tool-use-firewall - tags: mcp, firewall, security, ai, proxy, approval, human-in-the-loop, webhook ## @reaatech/tool-use-firewall-audit **Category:** Testing & Security · **Repo:** tool-use-firewall · **Status:** published v0.2.0 An audit logger for tool-use-firewall that records ALLOW, BLOCK, and APPROVAL_REQUIRED decisions with configurable verbosity levels, automatic sensitive data redaction, rotating file output, and optional HTTP forwarding to SIEM systems. Exports an `AuditLogger` class with a `log(event)` method and a `close()` flush method. - npm: https://www.npmjs.com/package/@reaatech/tool-use-firewall-audit - detail: https://reaatech.com/products/testing-security/tool-use-firewall/packages/tool-use-firewall-audit - repo: https://github.com/reaatech/tool-use-firewall - tags: mcp, firewall, security, ai, proxy, audit, logging, redaction, compliance ## @reaatech/tool-use-firewall-config **Category:** Testing & Security · **Repo:** tool-use-firewall · **Status:** published v0.2.0 Zod-based policy schema definitions and YAML policy file loader for the tool-use-firewall proxy. Exports `loadPolicyConfig(path)` to read and validate a YAML policy file, `validatePolicyFile(path)` to lint policies (including ReDoS safety checks), and typed `z.infer` config types for rate limits, costs, approvals, audits, and more. - npm: https://www.npmjs.com/package/@reaatech/tool-use-firewall-config - detail: https://reaatech.com/products/testing-security/tool-use-firewall/packages/tool-use-firewall-config - repo: https://github.com/reaatech/tool-use-firewall - tags: mcp, firewall, security, ai, proxy, policy, config, yaml, zod ## @reaatech/tool-use-firewall-core **Category:** Testing & Security · **Repo:** tool-use-firewall · **Status:** published v0.2.0 Core types, error classes, structured logger, sensitive data redactor, and ReDoS-safe regex utilities for the tool-use-firewall ecosystem. Exports TypeScript types (`RequestContext`, `Middleware`, `InterceptorResponse`), a typed error hierarchy (`FirewallError`, `RateLimitError`, `ValidationError`, `PolicyViolationError`, `BudgetExceededError`, `ApprovalRequiredError`), a JSON logger that writes to stderr, a `redact()` function with built-in patterns for API keys and tokens, and `safeRegExp()`/`isSafeRegex()` for ReDoS-safe regex compilation. - npm: https://www.npmjs.com/package/@reaatech/tool-use-firewall-core - detail: https://reaatech.com/products/testing-security/tool-use-firewall/packages/tool-use-firewall-core - repo: https://github.com/reaatech/tool-use-firewall - tags: mcp, firewall, security, ai, proxy, policy, llm, tool-use ## @reaatech/tool-use-firewall-policies **Category:** Testing & Security · **Repo:** tool-use-firewall · **Status:** published v0.2.0 A collection of middleware components—policy engine, rate limiter, cost tracker, argument validators, SQL validator, secret scanner, anomaly detector, and read-only enforcement—each implementing the `Middleware` interface for pluggable use in a tool-use-firewall interceptor pipeline. - npm: https://www.npmjs.com/package/@reaatech/tool-use-firewall-policies - detail: https://reaatech.com/products/testing-security/tool-use-firewall/packages/tool-use-firewall-policies - repo: https://github.com/reaatech/tool-use-firewall - tags: mcp, firewall, security, ai, proxy, policy, rate-limiting, cost-tracking, sql-validation ## @reaatech/tool-use-firewall-server **Category:** Testing & Security · **Repo:** tool-use-firewall · **Status:** published v0.2.0 An MCP proxy server that spawns upstream MCP servers as child processes, intercepts JSON-RPC `tools/call` messages, runs them through a configurable policy pipeline (rate limiter, cost tracker, secret scanner, argument validator, schema validator, policy engine, read-only check, anomaly detector, approval workflow, audit logger), and forwards allowed requests. Exports the `MCPProxyServer` class and the `tool-use-firewall` CLI binary. - npm: https://www.npmjs.com/package/@reaatech/tool-use-firewall-server - detail: https://reaatech.com/products/testing-security/tool-use-firewall/packages/tool-use-firewall-server - repo: https://github.com/reaatech/tool-use-firewall - tags: mcp, firewall, security, ai, proxy, cli, mcp-server, policy-enforcement # Evals & Quality > 64 packages — Agent and RAG eval harnesses, LLM-as-judge, prompt versioning. ## @reaatech/agent-eval-harness-cli **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** published v0.1.2 A CLI providing 7 subcommands (`eval`, `judge`, `compare`, `gate`, `golden`, `report`, `serve`) for running and managing LLM agent evaluations, including trajectory loading, multi-metric scoring, CI gate checks with exit codes, golden reference management, multi-format reporting (JSON, HTML, Markdown, PDF), and an MCP server exposing evaluation tools to AI coding agents. - npm: https://www.npmjs.com/package/@reaatech/agent-eval-harness-cli - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-cli - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-eval-harness-cost **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** published v0.1.0 Calculates per-task LLM token and tool invocation costs for AI agent trajectories, with budget enforcement and cost reporting. Exports functions like `calculateTrajectoryCost`, `checkBudget`, and `generateCostReport` that operate on `Trajectory` objects from `@reaatech/agent-eval-harness-types`. - npm: https://www.npmjs.com/package/@reaatech/agent-eval-harness-cost - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-cost - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-eval-harness-gate **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** published v0.1.2 A function that evaluates AI agent evaluation results against configurable quality, cost, latency, and correctness thresholds, returning a pass/fail summary for CI/CD gating. - npm: https://www.npmjs.com/package/@reaatech/agent-eval-harness-gate - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-gate - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-eval-harness-golden **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** published v0.1.0 A library for creating, managing, and comparing golden reference trajectories against candidate agent runs to detect regressions. It provides functions (`createGolden`, `compareAgainstGolden`, `batchCompare`) and a `GoldenCurator` class for structured curation workflows, returning diff analysis with turn-level similarity scores and regression details. - npm: https://www.npmjs.com/package/@reaatech/agent-eval-harness-golden - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-golden - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-eval-harness-infra **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** pending npm Terraform modules and environment configurations for deploying the agent-eval-harness application to AWS, Azure, GCP, OCI, Netlify, and Vercel, providing reusable infrastructure-as-code for compute, database, cache, and storage resources across each platform. - npm: pending — package not yet published as @reaatech/agent-eval-harness-infra - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-infra - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-eval-harness-judge **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** published v0.2.0 A provider-agnostic LLM-as-judge engine that scores agent responses on faithfulness, relevance, tool correctness, and overall quality using Claude, GPT-4, Gemini, or any OpenAI-compatible provider. Exports a `JudgeEngine` class with `judge` and `judgeBatch` methods, plus a `JudgeCalibrator` for calibrating scores against human labels using temperature scaling, isotonic regression, or linear regression. - npm: https://www.npmjs.com/package/@reaatech/agent-eval-harness-judge - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-judge - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-eval-harness-latency **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** published v0.1.0 A latency monitoring and SLA enforcement toolkit for AI agent evaluation, providing functions to compute P50/P90/P99 percentiles per turn and trajectory, detect anomalous turns, and validate against configurable latency budgets with severity-graded violations and optimization recommendations. - npm: https://www.npmjs.com/package/@reaatech/agent-eval-harness-latency - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-latency - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-eval-harness-mcp-server **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** published v0.1.2 An MCP (Model Context Protocol) server that exposes 13 evaluation tools across three layers—atomic judge operations, orchestrated suite runs, and CI gate operations—via stdio transport for integration with AI coding agents like Claude Desktop. It provides a `createMCPServer` function that returns an `EvalHarnessMCPServer` instance, with no external database dependency and session-scoped in-memory state. - npm: https://www.npmjs.com/package/@reaatech/agent-eval-harness-mcp-server - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-mcp-server - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-eval-harness-observability **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** published v0.1.1 Provides OpenTelemetry tracing, 7 pre-configured metrics, Pino-based structured logging with automatic PII redaction, and an in-memory dashboard manager with trend analysis and alerting for agent evaluation pipelines. Exports factory functions (`getLogger`, `getTracingManager`, `getMetricsManager`, `getDashboardManager`) and a `withTracing()` decorator. - npm: https://www.npmjs.com/package/@reaatech/agent-eval-harness-observability - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-observability - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-eval-harness-suite **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** published v0.1.2 A YAML-driven batch evaluation runner that executes multi-metric assessments across trajectory collections with configurable concurrency, then aggregates results into JSON, JUnit XML, CSV, or Markdown and supports statistical comparison between baseline and candidate runs. It provides `SuiteRunner`, `parseConfig`, `ResultsAggregator`, and threshold-checking utilities, and pairs with `@reaatech/agent-eval-harness-trajectory` for per-trajectory evaluation. - npm: https://www.npmjs.com/package/@reaatech/agent-eval-harness-suite - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-suite - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-eval-harness-tool-use **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** published v0.1.0 Validates tool selection, argument schema compliance, result hallucination, and integration for agent tool calls across trajectories, exporting functions like `validateToolCall`, `validateTrajectory`, and `verifyResult` that operate on `ToolCall` and `Turn` types from `@reaatech/agent-eval-harness-types`. - npm: https://www.npmjs.com/package/@reaatech/agent-eval-harness-tool-use - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-tool-use - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-eval-harness-trajectory **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** published v0.1.0 Parses JSONL turn files into validated trajectories, then scores them for coherence, goal completion, and conversation flow, and diffs candidate trajectories against golden references for regression detection. - npm: https://www.npmjs.com/package/@reaatech/agent-eval-harness-trajectory - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-trajectory - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-eval-harness-types **Category:** Evals & Quality · **Repo:** agent-eval-harness · **Status:** published v0.1.0 Canonical TypeScript domain types, Zod schemas, and interfaces for the agent-eval-harness ecosystem. Exports 19 interfaces (`Turn`, `Trajectory`, `EvalResult`, `JudgeScore`, `CostBreakdown`, `LatencyBudget`, `GoldenTrajectory`, `RegressionGate`, and more) plus 20 Zod schemas with full type inference, with no runtime dependencies beyond `zod`. - npm: https://www.npmjs.com/package/@reaatech/agent-eval-harness-types - detail: https://reaatech.com/products/evals-quality/agent-eval-harness/packages/agent-eval-harness-types - repo: https://github.com/reaatech/agent-eval-harness ## @reaatech/agent-replay **Category:** Evals & Quality · **Repo:** agent-replay · **Status:** published v0.1.0 A convenience re-export package that provides the complete public API of the Agent Replay ecosystem—core engine, LLM interceptors, and shared types—from a single import. - npm: https://www.npmjs.com/package/@reaatech/agent-replay - detail: https://reaatech.com/products/evals-quality/agent-replay/packages/agent-replay - repo: https://github.com/reaatech/agent-replay - tags: agent, replay, llm, debugging, testing ## @reaatech/agent-replay-cli **Category:** Evals & Quality · **Repo:** agent-replay · **Status:** published v0.1.0 A CLI tool for recording, replaying, debugging, and comparing AI agent traces, providing five subcommands (`record`, `replay`, `explore`, `diff`, `debug`) that operate on `.artrace.json` trace files. - npm: https://www.npmjs.com/package/@reaatech/agent-replay-cli - detail: https://reaatech.com/products/evals-quality/agent-replay/packages/agent-replay-cli - repo: https://github.com/reaatech/agent-replay - tags: agent, replay, llm, cli, debugging ## @reaatech/agent-replay-core **Category:** Evals & Quality · **Repo:** agent-replay · **Status:** published v0.1.0 Recording and replay engine for AI agent traces, providing a `RecordingEngine` to capture span-structured interactions with events and checkpoints, and a `ReplayEngine` to deterministically replay those traces in stubbed, live, or partial modes without consuming LLM tokens. - npm: https://www.npmjs.com/package/@reaatech/agent-replay-core - detail: https://reaatech.com/products/evals-quality/agent-replay/packages/agent-replay-core - repo: https://github.com/reaatech/agent-replay - tags: agent, replay, llm, debugging, testing ## @reaatech/agent-replay-integrations **Category:** Evals & Quality · **Repo:** agent-replay · **Status:** published v0.1.0 Provides callback handlers (`createLangChainHandler`) and state machine hooks (`createLangGraphHooks`) that record LangChain and LangGraph agent interactions into traces, returning handler objects compatible with each framework's interfaces. - npm: https://www.npmjs.com/package/@reaatech/agent-replay-integrations - detail: https://reaatech.com/products/evals-quality/agent-replay/packages/agent-replay-integrations - repo: https://github.com/reaatech/agent-replay - tags: agent, replay, llm, langchain, langgraph, integration ## @reaatech/agent-replay-interceptors **Category:** Evals & Quality · **Repo:** agent-replay · **Status:** published v0.1.0 Monkey-patches OpenAI and Anthropic SDK clients to transparently record all LLM API calls into Agent Replay traces, providing `OpenAIInterceptor` and `AnthropicInterceptor` classes that wrap `client.chat.completions.create` and `client.messages.create` respectively. Requires `@reaatech/agent-replay-core` for the `RecordingEngine`. - npm: https://www.npmjs.com/package/@reaatech/agent-replay-interceptors - detail: https://reaatech.com/products/evals-quality/agent-replay/packages/agent-replay-interceptors - repo: https://github.com/reaatech/agent-replay - tags: agent, replay, llm, openai, anthropic, interceptor ## @reaatech/agent-replay-shared **Category:** Evals & Quality · **Repo:** agent-replay · **Status:** published v0.1.0 Shared types, interfaces, error classes, and configuration for the Agent Replay ecosystem, providing the canonical trace model shapes, LLM provider abstractions, and storage contracts as pure TypeScript exports with zero runtime dependencies. - npm: https://www.npmjs.com/package/@reaatech/agent-replay-shared - detail: https://reaatech.com/products/evals-quality/agent-replay/packages/agent-replay-shared - repo: https://github.com/reaatech/agent-replay - tags: agent, replay, llm, types ## @reaatech/agent-replay-web-ui **Category:** Evals & Quality · **Repo:** agent-replay · **Status:** pending npm Web-based trace viewer for Agent Replay that provides an interactive UI for exploring recorded agent traces, including span timelines, event inspection, checkpoint navigation, and diff visualization. - npm: pending — package not yet published as @reaatech/agent-replay-web-ui - detail: https://reaatech.com/products/evals-quality/agent-replay/packages/agent-replay-web-ui - repo: https://github.com/reaatech/agent-replay ## @reaatech/agents-markdown **Category:** Evals & Quality · **Repo:** agents-md-kit · **Status:** published v1.0.1 Core domain types (`AgentsMdDocument`, `SkillMdDocument`, `Finding`, `LintResult`, `ValidationResult`), Zod validation schemas, and shared utilities for the `@reaatech/agents-markdown-*` ecosystem. Exports TypeScript interfaces, Zod schemas, and utility functions (`assertNever`, `delay`, `groupBy`, etc.) with no runtime dependencies. - npm: https://www.npmjs.com/package/@reaatech/agents-markdown - detail: https://reaatech.com/products/evals-quality/agents-md-kit/packages/agents-markdown - repo: https://github.com/reaatech/agents-md-kit ## @reaatech/agents-markdown-cli **Category:** Evals & Quality · **Repo:** agents-md-kit · **Status:** published v1.0.1 A CLI for linting, validating, scaffolding, and formatting AGENTS.md and SKILL.md files, providing five subcommands (`lint`, `validate`, `scaffold`, `format`, `examples`) with multi-format output (console, JSON, HTML, Markdown) and CI-friendly exit codes. Built on Commander, it also exports utility functions for programmatic use. - npm: https://www.npmjs.com/package/@reaatech/agents-markdown-cli - detail: https://reaatech.com/products/evals-quality/agents-md-kit/packages/agents-markdown-cli - repo: https://github.com/reaatech/agents-md-kit ## @reaatech/agents-markdown-linter **Category:** Evals & Quality · **Repo:** agents-md-kit · **Status:** published v1.0.1 A linting engine for AGENTS.md and SKILL.md files that provides 18 built-in rules across style, content, and best-practice categories, exposed as `runLintRules`, `registerRule`, and `runAutoFix` functions. It depends on `@reaatech/agents-markdown-parser` for document parsing and outputs findings in a standard `Finding[]` format. - npm: https://www.npmjs.com/package/@reaatech/agents-markdown-linter - detail: https://reaatech.com/products/evals-quality/agents-md-kit/packages/agents-markdown-linter - repo: https://github.com/reaatech/agents-md-kit ## @reaatech/agents-markdown-mcp-server **Category:** Evals & Quality · **Repo:** agents-md-kit · **Status:** published v1.0.1 An MCP server that exposes five tools—`lint_agents_md`, `validate_agents_md`, `validate_skill_md`, `scaffold_agent`, and `get_examples`—for working with agent markdown files via the Model Context Protocol. It exports `createMcpServer()` (returns a configured `Server` instance from `@modelcontextprotocol/sdk`) and `startMcpServer(transportType?)` (starts the server over Stdio or StreamableHTTP). - npm: https://www.npmjs.com/package/@reaatech/agents-markdown-mcp-server - detail: https://reaatech.com/products/evals-quality/agents-md-kit/packages/agents-markdown-mcp-server - repo: https://github.com/reaatech/agents-md-kit ## @reaatech/agents-markdown-observability **Category:** Evals & Quality · **Repo:** agents-md-kit · **Status:** published v1.0.1 Pino-based structured logging, OpenTelemetry metrics and tracing, and dashboard aggregation for the `@reaatech/agents-markdown-*` ecosystem, exposed as functions (`info`, `error`, `recordOperation`, `buildDashboardSummary`) and a singleton `MetricsManager` class. - npm: https://www.npmjs.com/package/@reaatech/agents-markdown-observability - detail: https://reaatech.com/products/evals-quality/agents-md-kit/packages/agents-markdown-observability - repo: https://github.com/reaatech/agents-md-kit ## @reaatech/agents-markdown-parser **Category:** Evals & Quality · **Repo:** agents-md-kit · **Status:** published v1.0.1 Parses AGENTS.md and SKILL.md markdown files into typed documents with YAML frontmatter extraction, section hierarchy, table parsing, and code block extraction. Exports async functions like `parseMarkdown` and `parseMarkdownFiles` that return `AgentsMdDocument` or `SkillMdDocument` objects, plus utilities for navigating sections, validating frontmatter, and extracting tables and code blocks. Built on remark and unified. - npm: https://www.npmjs.com/package/@reaatech/agents-markdown-parser - detail: https://reaatech.com/products/evals-quality/agents-md-kit/packages/agents-markdown-parser - repo: https://github.com/reaatech/agents-md-kit ## @reaatech/agents-markdown-reporter **Category:** Evals & Quality · **Repo:** agents-md-kit · **Status:** published v1.0.1 Exports a set of reporter functions (`reportLintResult`, `reportJsonLintResult`, `reportHtmlLintResult`, `reportMarkdownLintResult`, and their validation counterparts) that format lint and validation results into console (ANSI-colorized), JSON, self-contained HTML, or GitHub-flavored Markdown output. - npm: https://www.npmjs.com/package/@reaatech/agents-markdown-reporter - detail: https://reaatech.com/products/evals-quality/agents-md-kit/packages/agents-markdown-reporter - repo: https://github.com/reaatech/agents-md-kit ## @reaatech/agents-markdown-scaffold **Category:** Evals & Quality · **Repo:** agents-md-kit · **Status:** published v1.0.1 A function that generates AGENTS.md and SKILL.md files from Handlebars templates, creating a complete agent directory structure with one skill file per listed skill ID. - npm: https://www.npmjs.com/package/@reaatech/agents-markdown-scaffold - detail: https://reaatech.com/products/evals-quality/agents-md-kit/packages/agents-markdown-scaffold - repo: https://github.com/reaatech/agents-md-kit ## @reaatech/agents-markdown-validator **Category:** Evals & Quality · **Repo:** agents-md-kit · **Status:** published v1.0.1 A Zod-based validation engine for AGENTS.md and SKILL.md files that checks frontmatter structure, required sections, section ordering, skill references, MCP tools tables, and content quality against the specification. It exports `validate`, `validateAgentsMd`, and `validateSkillMd` functions that take parsed document objects (from `@reaatech/agents-markdown-parser`) and return structured validation results with errors and warnings. - npm: https://www.npmjs.com/package/@reaatech/agents-markdown-validator - detail: https://reaatech.com/products/evals-quality/agents-md-kit/packages/agents-markdown-validator - repo: https://github.com/reaatech/agents-md-kit ## @reaatech/classifier-evals **Category:** Evals & Quality · **Repo:** classifier-evals · **Status:** published v0.1.1 Canonical TypeScript types, Zod schemas, and shared utilities (structured logging, OpenTelemetry tracing/metrics, PII redaction, hashing) for the classifier-evals evaluation ecosystem. Exports 40+ Zod-validated types and schemas covering classification results, datasets, confusion matrices, metrics, and evaluation runs, plus a Pino-based logger and OpenTelemetry instrumentation. - npm: https://www.npmjs.com/package/@reaatech/classifier-evals - detail: https://reaatech.com/products/evals-quality/classifier-evals/packages/classifier-evals - repo: https://github.com/reaatech/classifier-evals ## @reaatech/classifier-evals-cli **Category:** Evals & Quality · **Repo:** classifier-evals · **Status:** published v0.1.1 A CLI for running classifier evaluations, comparing models, checking regression gates, and exporting results, built on Commander.js and the `@reaatech/classifier-evals-*` ecosystem. - npm: https://www.npmjs.com/package/@reaatech/classifier-evals-cli - detail: https://reaatech.com/products/evals-quality/classifier-evals/packages/classifier-evals-cli - repo: https://github.com/reaatech/classifier-evals ## @reaatech/classifier-evals-dataset **Category:** Evals & Quality · **Repo:** classifier-evals · **Status:** published v0.1.1 A dataset loading and validation utility for classifier evaluation, supporting CSV, JSON, and JSONL formats. Provides functions (`loadDataset`, `validateDataset`, `splitDataset`) for loading, schema validation, stratified train/test splitting, K-fold cross-validation, label normalization, alias resolution, and hierarchical label handling. - npm: https://www.npmjs.com/package/@reaatech/classifier-evals-dataset - detail: https://reaatech.com/products/evals-quality/classifier-evals/packages/classifier-evals-dataset - repo: https://github.com/reaatech/classifier-evals ## @reaatech/classifier-evals-exporters **Category:** Evals & Quality · **Repo:** classifier-evals · **Status:** published v0.1.1 Export classifier evaluation results as JSON, HTML, Arize Phoenix traces, or Langfuse traces. Provides four functions (`exportToJson`, `exportToHtml`, `exportToPhoenix`, `exportToLangfuse`) that accept an `EvalRun` object and format-specific options. - npm: https://www.npmjs.com/package/@reaatech/classifier-evals-exporters - detail: https://reaatech.com/products/evals-quality/classifier-evals/packages/classifier-evals-exporters - repo: https://github.com/reaatech/classifier-evals ## @reaatech/classifier-evals-gates **Category:** Evals & Quality · **Repo:** classifier-evals · **Status:** published v0.1.1 A gate evaluation engine that checks classifier metrics (accuracy, F1, precision, recall) against threshold, baseline-comparison, and distribution gates, returning pass/fail results and CI output formats (GitHub Actions annotations, JUnit XML, PR comment markdown). It provides a `createGateEngine()` function that returns an object with `evaluateGates()`, `formatForGitHubActions()`, and `formatAsJUnit()` methods, and pairs with `@reaatech/classifier-evals-metrics` for metric calculation. - npm: https://www.npmjs.com/package/@reaatech/classifier-evals-gates - detail: https://reaatech.com/products/evals-quality/classifier-evals/packages/classifier-evals-gates - repo: https://github.com/reaatech/classifier-evals ## @reaatech/classifier-evals-judge **Category:** Evals & Quality · **Repo:** classifier-evals · **Status:** published v0.1.1 A function that creates an LLM-as-judge engine for evaluating classifier outputs, supporting Anthropic and OpenAI models with configurable consensus voting, real-time cost tracking, and built-in prompt templates for classification evaluation, ambiguity detection, and error categorization. - npm: https://www.npmjs.com/package/@reaatech/classifier-evals-judge - detail: https://reaatech.com/products/evals-quality/classifier-evals/packages/classifier-evals-judge - repo: https://github.com/reaatech/classifier-evals ## @reaatech/classifier-evals-mcp-server **Category:** Evals & Quality · **Repo:** classifier-evals · **Status:** published v0.1.1 An MCP server that exposes five tools (`run_eval`, `check_gates`, `compare_models`, `llm_judge`, `generate_report`) for running classifier evaluation pipelines, checking regression gates, comparing models, and generating reports, communicating over stdio transport with any MCP-compatible client. - npm: https://www.npmjs.com/package/@reaatech/classifier-evals-mcp-server - detail: https://reaatech.com/products/evals-quality/classifier-evals/packages/classifier-evals-mcp-server - repo: https://github.com/reaatech/classifier-evals ## @reaatech/classifier-evals-metrics **Category:** Evals & Quality · **Repo:** classifier-evals · **Status:** published v0.1.1 A function that computes confusion matrices, 14 classification metrics (accuracy, macro/micro/weighted precision/recall/F1, MCC, Cohen's Kappa), model comparison with McNemar's test and Cohen's d, and evaluation run construction from classification results. - npm: https://www.npmjs.com/package/@reaatech/classifier-evals-metrics - detail: https://reaatech.com/products/evals-quality/classifier-evals/packages/classifier-evals-metrics - repo: https://github.com/reaatech/classifier-evals ## @reaatech/context-window-planner **Category:** Evals & Quality · **Repo:** context-window-planner · **Status:** published v0.1.0 A TypeScript library providing typed context items, packing strategies, and tokenizer adapters for deciding what to include, summarize, or drop when fitting prompts into LLM context windows. It exports factory functions for six context item primitives (SystemPrompt, ConversationTurn, RAGChunk, ToolSchema, ToolResult, GenerationBuffer), four packing strategies (priority-greedy, sliding-window, summarize-and-replace, RAG relevance), and three tokenizer adapters (OpenAI/tiktoken, Anthropic approximate, mock), all orchestrated through a `ContextPlannerBuilder` class. - npm: https://www.npmjs.com/package/@reaatech/context-window-planner - detail: https://reaatech.com/products/evals-quality/context-window-planner/packages/context-window-planner - repo: https://github.com/reaatech/context-window-planner - tags: llm, context-window, token-budget, packing, rag, conversation, typescript ## @reaatech/context-window-planner-cli **Category:** Evals & Quality · **Repo:** context-window-planner · **Status:** published v0.1.0 A CLI that reads a JSON context-window planning request from stdin and writes a packing plan (included, summarized, and dropped items with token counts) to stdout. - npm: https://www.npmjs.com/package/@reaatech/context-window-planner-cli - detail: https://reaatech.com/products/evals-quality/context-window-planner/packages/context-window-planner-cli - repo: https://github.com/reaatech/context-window-planner ## @reaatech/llm-judge-bias **Category:** Evals & Quality · **Repo:** llm-judge-toolkit · **Status:** published v0.1.1 A set of classes (`PositionBiasDetector`, `LengthBiasDetector`, `StyleBiasDetector`, and `ComprehensiveBiasDetector`) that detect systematic biases—position, length, and style—in LLM judgments by comparing scores across controlled variations (e.g., swapped order, length correlation, style transformations). Requires a judge function (e.g., an LLM call) to evaluate candidates or responses. - npm: https://www.npmjs.com/package/@reaatech/llm-judge-bias - detail: https://reaatech.com/products/evals-quality/llm-judge-toolkit/packages/llm-judge-bias - repo: https://github.com/reaatech/llm-judge-toolkit ## @reaatech/llm-judge-cache **Category:** Evals & Quality · **Repo:** llm-judge-toolkit · **Status:** published v0.1.1 A CacheManager facade with pluggable in-memory, file-system, and Redis backends for caching LLM judgment results, using SHA-256 content-addressed keys and configurable TTL. - npm: https://www.npmjs.com/package/@reaatech/llm-judge-cache - detail: https://reaatech.com/products/evals-quality/llm-judge-toolkit/packages/llm-judge-cache - repo: https://github.com/reaatech/llm-judge-toolkit ## @reaatech/llm-judge-calibration **Category:** Evals & Quality · **Repo:** llm-judge-toolkit · **Status:** published v0.1.1 A TypeScript library that measures how accurately an LLM judge system classifies text against human-labeled gold-standard datasets, providing Cohen's kappa, confusion matrices, precision/recall/F1 scores, and drift detection. It exports `CalibrationRunner`, `CalibrationMetrics`, `DatasetManager`, and `DriftDetector` classes for batch evaluation and ongoing monitoring. - npm: https://www.npmjs.com/package/@reaatech/llm-judge-calibration - detail: https://reaatech.com/products/evals-quality/llm-judge-toolkit/packages/llm-judge-calibration - repo: https://github.com/reaatech/llm-judge-toolkit ## @reaatech/llm-judge-cli **Category:** Evals & Quality · **Repo:** llm-judge-toolkit · **Status:** published v0.1.1 A CLI that evaluates LLM responses against criteria (faithfulness, relevance, coherence, safety, tool-use) and calibrates judgments against human labels, reading JSONL input and outputting scored results via `evaluate` and `calibrate` subcommands. - npm: https://www.npmjs.com/package/@reaatech/llm-judge-cli - detail: https://reaatech.com/products/evals-quality/llm-judge-toolkit/packages/llm-judge-cli - repo: https://github.com/reaatech/llm-judge-toolkit ## @reaatech/llm-judge-consensus **Category:** Evals & Quality · **Repo:** llm-judge-toolkit · **Status:** published v0.1.1 Provides consensus strategies (majority voting, weighted voting, and a cheap-first tiebreaker) as classes implementing a shared `ConsensusStrategy` interface, combining individual judgment scores into a final evaluation with an agreement score. - npm: https://www.npmjs.com/package/@reaatech/llm-judge-consensus - detail: https://reaatech.com/products/evals-quality/llm-judge-toolkit/packages/llm-judge-consensus - repo: https://github.com/reaatech/llm-judge-toolkit ## @reaatech/llm-judge-engine **Category:** Evals & Quality · **Repo:** llm-judge-toolkit · **Status:** published v0.1.1 Orchestrates LLM-based judgment calls with automatic retry, caching, rate limiting, and a typed event bus, exposing a `JudgmentEngine` class that takes a provider, template, and config. - npm: https://www.npmjs.com/package/@reaatech/llm-judge-engine - detail: https://reaatech.com/products/evals-quality/llm-judge-toolkit/packages/llm-judge-engine - repo: https://github.com/reaatech/llm-judge-toolkit ## @reaatech/llm-judge-infra **Category:** Evals & Quality · **Repo:** llm-judge-toolkit · **Status:** published v0.1.1 Infrastructure utilities for LLM judgment pipelines, providing a `CostTracker` with period-aware budget enforcement, a `BatchProcessor` with configurable concurrency and retry, a `MetricsCollector`, and structured Pino logging helpers. Depends on `pino` at runtime. - npm: https://www.npmjs.com/package/@reaatech/llm-judge-infra - detail: https://reaatech.com/products/evals-quality/llm-judge-toolkit/packages/llm-judge-infra - repo: https://github.com/reaatech/llm-judge-toolkit ## @reaatech/llm-judge-providers **Category:** Evals & Quality · **Repo:** llm-judge-toolkit · **Status:** published v0.1.1 A factory-pattern provider that exposes `ProviderFactory.create()` and `ProviderFactory.fromEnv()` to instantiate OpenAI, Anthropic, or local (OpenAI-compatible) LLM clients, all conforming to a shared `LLMProvider` interface with built-in cost calculation and health checks. It lazily loads the `openai` or `@anthropic-ai/sdk` packages only when the corresponding provider is used. - npm: https://www.npmjs.com/package/@reaatech/llm-judge-providers - detail: https://reaatech.com/products/evals-quality/llm-judge-toolkit/packages/llm-judge-providers - repo: https://github.com/reaatech/llm-judge-toolkit ## @reaatech/llm-judge-templates **Category:** Evals & Quality · **Repo:** llm-judge-toolkit · **Status:** published v0.1.1 A set of evaluation prompt templates (faithfulness, relevance, coherence, safety, tool-use) that implement a `JudgmentTemplate` interface with `buildPrompt` and `parseResponse` methods, returning structured JSON judgments with score, reasoning, confidence, and metadata. - npm: https://www.npmjs.com/package/@reaatech/llm-judge-templates - detail: https://reaatech.com/products/evals-quality/llm-judge-toolkit/packages/llm-judge-templates - repo: https://github.com/reaatech/llm-judge-toolkit ## @reaatech/llm-judge-types **Category:** Evals & Quality · **Repo:** llm-judge-toolkit · **Status:** published v0.1.1 Shared TypeScript types, Zod schemas, and error classes for the LLM Judge Toolkit ecosystem, providing 70+ exported types and 6 typed error classes with zero runtime dependencies beyond Zod. - npm: https://www.npmjs.com/package/@reaatech/llm-judge-types - detail: https://reaatech.com/products/evals-quality/llm-judge-toolkit/packages/llm-judge-types - repo: https://github.com/reaatech/llm-judge-toolkit ## @reaatech/prompt-version-control **Category:** Evals & Quality · **Repo:** prompt-version-control · **Status:** published v0.1.0 A typed TypeScript client class (`PromptVersionControlClient` or `PVCClient`) for the Prompt Version Control API, providing authenticated HTTP access with automatic exponential-backoff retry on 5xx/network errors, configurable `AbortController`-based timeouts, and optional in-memory LRU caching with TTL and max-entries eviction. - npm: https://www.npmjs.com/package/@reaatech/prompt-version-control - detail: https://reaatech.com/products/evals-quality/prompt-version-control/packages/prompt-version-control - repo: https://github.com/reaatech/prompt-version-control - tags: prompt, version-control, sdk, typescript ## @reaatech/prompt-version-control-cli **Category:** Evals & Quality · **Repo:** prompt-version-control · **Status:** published v0.1.0 A CLI tool (`pvc`) for managing prompt templates, their versions, and lifecycle tags (draft/staging/production) from the terminal, built on Clipanion 4 with persistent configuration stored in `~/.pvcrc`. - npm: https://www.npmjs.com/package/@reaatech/prompt-version-control-cli - detail: https://reaatech.com/products/evals-quality/prompt-version-control/packages/prompt-version-control-cli - repo: https://github.com/reaatech/prompt-version-control - tags: prompt, version-control, cli ## @reaatech/prompt-version-control-mcp **Category:** Evals & Quality · **Repo:** prompt-version-control · **Status:** published v0.1.0 An MCP server that exposes a single `prompt.get` tool, which fetches a production-tagged prompt from a Prompt Version Control API server and renders it with Handlebars template interpolation. Requires `PVC_API_URL` and `PVC_API_KEY` environment variables to connect to the API server. - npm: https://www.npmjs.com/package/@reaatech/prompt-version-control-mcp - detail: https://reaatech.com/products/evals-quality/prompt-version-control/packages/prompt-version-control-mcp - repo: https://github.com/reaatech/prompt-version-control - tags: prompt, version-control, mcp, model-context-protocol ## @reaatech/prompt-version-control-server **Category:** Evals & Quality · **Repo:** prompt-version-control · **Status:** published v0.1.0 A Hono 4 server that provides Git-like version control for AI prompts, including CRUD, SHA-256 checksummed versioning, tag-based lifecycle (draft/staging/production), eval-gated promotion, A/B deployment with weighted traffic splitting, metrics ingestion, and webhook subscriptions, backed by Prisma and PostgreSQL. - npm: https://www.npmjs.com/package/@reaatech/prompt-version-control-server - detail: https://reaatech.com/products/evals-quality/prompt-version-control/packages/prompt-version-control-server - repo: https://github.com/reaatech/prompt-version-control - tags: prompt, version-control, api, hono, prisma ## @reaatech/prompt-version-control-shared **Category:** Evals & Quality · **Repo:** prompt-version-control · **Status:** published v0.1.0 Canonical TypeScript types, Zod schemas, and shared utilities (template rendering, API key generation, checksumming) for the Prompt Version Control ecosystem. Exports 25+ Zod schemas with inferred types, plus Handlebars-based prompt interpolation and cryptographic utilities, with only `zod` and `handlebars` as runtime dependencies. - npm: https://www.npmjs.com/package/@reaatech/prompt-version-control-shared - detail: https://reaatech.com/products/evals-quality/prompt-version-control/packages/prompt-version-control-shared - repo: https://github.com/reaatech/prompt-version-control - tags: prompt, version-control, types, schemas ## @reaatech/rag-eval-cli **Category:** Evals & Quality · **Repo:** rag-eval-pack · **Status:** published v0.1.0 A CLI that runs RAG evaluation suites, quality gates, run comparisons, cost breakdowns, markdown reports, LLM-based judging, and an MCP server, exposed as the `rag-eval-pack` command. It also re-exports the full programmatic API from all `@reaatech/rag-eval-*` packages as a single importable library. - npm: https://www.npmjs.com/package/@reaatech/rag-eval-cli - detail: https://reaatech.com/products/evals-quality/rag-eval-pack/packages/rag-eval-cli - repo: https://github.com/reaatech/rag-eval-pack ## @reaatech/rag-eval-core **Category:** Evals & Quality · **Repo:** rag-eval-pack · **Status:** published v0.1.0 Canonical TypeScript types and Zod schemas for RAG evaluation data shapes. Exports 18+ types (`EvaluationSample`, `EvalSuiteConfig`, `SampleEvalResult`, `GateConfig`, `JudgeConfig`, etc.) and two Zod schemas (`EvaluationSampleSchema`, `EvalSuiteConfigSchema`) for runtime validation, with zero runtime dependencies beyond `zod`. - npm: https://www.npmjs.com/package/@reaatech/rag-eval-core - detail: https://reaatech.com/products/evals-quality/rag-eval-pack/packages/rag-eval-core - repo: https://github.com/reaatech/rag-eval-pack ## @reaatech/rag-eval-cost **Category:** Evals & Quality · **Repo:** rag-eval-pack · **Status:** published v0.1.0 Cost tracking, pricing, budgeting, and reporting infrastructure for RAG evaluations, providing `CostTracker`, `Pricing`, `BudgetManager`, and `CostReporter` classes that track per-sample token consumption, enforce budget limits with configurable alert thresholds, and generate cost reports in JSON and JUnit XML formats. - npm: https://www.npmjs.com/package/@reaatech/rag-eval-cost - detail: https://reaatech.com/products/evals-quality/rag-eval-pack/packages/rag-eval-cost - repo: https://github.com/reaatech/rag-eval-pack ## @reaatech/rag-eval-dataset **Category:** Evals & Quality · **Repo:** rag-eval-pack · **Status:** published v0.1.0 A Zod-validated dataset loader and validator for RAG evaluation samples, supporting JSONL, JSON, and YAML formats with duplicate detection, synthetic generation from templates, and version tracking. Exports `DatasetLoader`, `DatasetValidator`, and `loadEvalConfig` functions. - npm: https://www.npmjs.com/package/@reaatech/rag-eval-dataset - detail: https://reaatech.com/products/evals-quality/rag-eval-pack/packages/rag-eval-dataset - repo: https://github.com/reaatech/rag-eval-pack ## @reaatech/rag-eval-gate **Category:** Evals & Quality · **Repo:** rag-eval-pack · **Status:** published v0.1.0 A quality gate engine for RAG evaluation pipelines that enforces threshold-based metric checks and baseline regression detection, returning a `GateResult` object with pass/fail status and per-gate failure messages. It pairs with `@reaatech/rag-eval-core` for evaluation result types and is designed for CI/CD integration with formatted output and configurable exit codes. - npm: https://www.npmjs.com/package/@reaatech/rag-eval-gate - detail: https://reaatech.com/products/evals-quality/rag-eval-pack/packages/rag-eval-gate - repo: https://github.com/reaatech/rag-eval-pack ## @reaatech/rag-eval-judge **Category:** Evals & Quality · **Repo:** rag-eval-pack · **Status:** published v0.1.0 A TypeScript class (`JudgeEngine`) that uses an LLM (Anthropic, OpenAI, or Google) to score RAG outputs on metrics like faithfulness and relevance, with optional consensus voting across multiple models and calibration against human labels. - npm: https://www.npmjs.com/package/@reaatech/rag-eval-judge - detail: https://reaatech.com/products/evals-quality/rag-eval-pack/packages/rag-eval-judge - repo: https://github.com/reaatech/rag-eval-pack ## @reaatech/rag-eval-mcp-server **Category:** Evals & Quality · **Repo:** rag-eval-pack · **Status:** published v0.1.0 An MCP server that exposes RAG evaluation tools as a three-layer API of atomic judge operations, orchestrated suite runs, and CI-style regression gates, providing `createMcpServer()` and `startMcpServer()` functions for integration with MCP clients like Claude Desktop or Cursor. - npm: https://www.npmjs.com/package/@reaatech/rag-eval-mcp-server - detail: https://reaatech.com/products/evals-quality/rag-eval-pack/packages/rag-eval-mcp-server - repo: https://github.com/reaatech/rag-eval-pack ## @reaatech/rag-eval-metrics **Category:** Evals & Quality · **Repo:** rag-eval-pack · **Status:** published v0.1.0 Provides four heuristic metric scorers (faithfulness, relevance, context precision, context recall) for evaluating RAG outputs, plus a `MetricsEngine` orchestrator that runs them in parallel with configurable concurrency. Each scorer is a class with a `score` method that returns a numeric score and supporting details, using only NLP libraries (`compromise`, `natural`) with no LLM calls. - npm: https://www.npmjs.com/package/@reaatech/rag-eval-metrics - detail: https://reaatech.com/products/evals-quality/rag-eval-pack/packages/rag-eval-metrics - repo: https://github.com/reaatech/rag-eval-pack ## @reaatech/rag-eval-observability **Category:** Evals & Quality · **Repo:** rag-eval-pack · **Status:** published v0.1.0 Provides structured JSON logging via Pino, OpenTelemetry tracing, and OpenTelemetry metrics specifically for RAG evaluation pipelines, exporting functions like `createLogger`, `traceEvalRun`, and `recordEvalRun`. - npm: https://www.npmjs.com/package/@reaatech/rag-eval-observability - detail: https://reaatech.com/products/evals-quality/rag-eval-pack/packages/rag-eval-observability - repo: https://github.com/reaatech/rag-eval-pack ## @reaatech/rag-eval-suite **Category:** Evals & Quality · **Repo:** rag-eval-pack · **Status:** published v0.1.0 A class (`EvaluationSuite`) that orchestrates RAG evaluation runs by executing heuristic metrics, optional LLM judge scoring, cost tracking, and quality gates against a dataset, returning a `SuiteRunResult` with aggregated metrics and gate pass/fail status. - npm: https://www.npmjs.com/package/@reaatech/rag-eval-suite - detail: https://reaatech.com/products/evals-quality/rag-eval-pack/packages/rag-eval-suite - repo: https://github.com/reaatech/rag-eval-pack # Observability & Cost > 37 packages — OTel GenAI semconv, cost telemetry, semantic caching, model routing. ## @reaatech/agent-budget-cli **Category:** Observability & Cost · **Repo:** agent-budget-controller · **Status:** published v0.1.1 A CLI that installs a global `agent-budget` binary for managing agent budgets — defining budgets, checking remaining spend, listing active scopes, generating spend reports, simulating pre-flight checks, and manually resetting budgets. - npm: https://www.npmjs.com/package/@reaatech/agent-budget-cli - detail: https://reaatech.com/products/observability-cost/agent-budget-controller/packages/agent-budget-cli - repo: https://github.com/reaatech/agent-budget-controller ## @reaatech/agent-budget-engine **Category:** Observability & Cost · **Repo:** agent-budget-controller · **Status:** published v0.1.1 A budget enforcement engine that provides pre-flight cost checks, real-time spend recording, and per-scope state machine transitions (Active → Warned → Degraded → Stopped) with auto-downgrade to cheaper models and expensive tool filtering. Exports a `BudgetController` class that orchestrates spend tracking, pricing, and policy evaluation, and pairs with `@reaatech/agent-budget-spend-tracker` and `@reaatech/agent-budget-pricing` at runtime. - npm: https://www.npmjs.com/package/@reaatech/agent-budget-engine - detail: https://reaatech.com/products/observability-cost/agent-budget-controller/packages/agent-budget-engine - repo: https://github.com/reaatech/agent-budget-controller ## @reaatech/agent-budget-llm-router-plugin **Category:** Observability & Cost · **Repo:** agent-budget-controller · **Status:** published v0.1.1 A Fastify plugin that adds budget-aware routing to LLM Router, filtering model candidates by remaining budget and blocking requests when budgets are exhausted. It installs as the highest-priority strategy in the routing chain, evaluating before semantic and latency-based routing, and requires `@reaatech/agent-budget-engine` and `@reaatech/agent-budget-spend-tracker` at runtime. - npm: https://www.npmjs.com/package/@reaatech/agent-budget-llm-router-plugin - detail: https://reaatech.com/products/observability-cost/agent-budget-controller/packages/agent-budget-llm-router-plugin - repo: https://github.com/reaatech/agent-budget-controller ## @reaatech/agent-budget-middleware **Category:** Observability & Cost · **Repo:** agent-budget-controller · **Status:** published v0.1.1 Express/Fastify middleware and a direct SDK (`BudgetInterceptor`) that enforces per-scope budgets on agent requests by checking estimated cost, auto-downgrading models, filtering expensive tools, and recording spend — all before the LLM call reaches your application code. - npm: https://www.npmjs.com/package/@reaatech/agent-budget-middleware - detail: https://reaatech.com/products/observability-cost/agent-budget-controller/packages/agent-budget-middleware - repo: https://github.com/reaatech/agent-budget-controller ## @reaatech/agent-budget-otel-bridge **Category:** Observability & Cost · **Repo:** agent-budget-controller · **Status:** published v0.1.1 Converts OpenTelemetry GenAI spans into budget-tracked spend entries in real time by feeding span attributes to a `BudgetController`. Provides a `SpanListener` class that you call with span data from any OTel-compatible tracer. - npm: https://www.npmjs.com/package/@reaatech/agent-budget-otel-bridge - detail: https://reaatech.com/products/observability-cost/agent-budget-controller/packages/agent-budget-otel-bridge - repo: https://github.com/reaatech/agent-budget-controller ## @reaatech/agent-budget-pricing **Category:** Observability & Cost · **Repo:** agent-budget-controller · **Status:** published v0.1.1 A pricing engine that computes LLM token costs using built-in or custom pricing tables, with LRU-cached lookups and model name normalization. Exports a `PricingEngine` class with `computeCost`, `estimateCost`, and `lookup` methods, plus a `ModelNormalizer` for alias resolution. - npm: https://www.npmjs.com/package/@reaatech/agent-budget-pricing - detail: https://reaatech.com/products/observability-cost/agent-budget-controller/packages/agent-budget-pricing - repo: https://github.com/reaatech/agent-budget-controller ## @reaatech/agent-budget-spend-tracker **Category:** Observability & Cost · **Repo:** agent-budget-controller · **Status:** published v0.1.1 A circular-buffer-based in-memory spend tracker that records cost events and provides O(1) per-scope spend lookups, sliding-window rate calculations, cost projections, and anomaly detection—exposed as a `SpendStore` class with zero external dependencies. - npm: https://www.npmjs.com/package/@reaatech/agent-budget-spend-tracker - detail: https://reaatech.com/products/observability-cost/agent-budget-controller/packages/agent-budget-spend-tracker - repo: https://github.com/reaatech/agent-budget-controller ## @reaatech/agent-budget-types **Category:** Observability & Cost · **Repo:** agent-budget-controller · **Status:** published v0.1.1 Zod-validated TypeScript types, enums, and error classes defining budget scopes, policies, enforcement actions, spend entries, and state transitions for the agent-budget-controller ecosystem. Exports interfaces, enums, and Zod schemas with zero runtime dependencies beyond `zod`. - npm: https://www.npmjs.com/package/@reaatech/agent-budget-types - detail: https://reaatech.com/products/observability-cost/agent-budget-controller/packages/agent-budget-types - repo: https://github.com/reaatech/agent-budget-controller ## @reaatech/llm-cache **Category:** Observability & Cost · **Repo:** llm-cache · **Status:** published v0.1.0 A caching engine for LLM calls that provides both exact-match (SHA-256 hash) and semantic (cosine similarity on embeddings) cache lookups, with model-aware fingerprinting, use-case segmentation, and adaptive TTL. It exports a `CacheEngine` class that requires `StorageAdapter` and `VectorStorageAdapter` implementations (e.g., in-memory, Redis, DynamoDB) and an `Embedder` for semantic matching. - npm: https://www.npmjs.com/package/@reaatech/llm-cache - detail: https://reaatech.com/products/observability-cost/llm-cache/packages/llm-cache - repo: https://github.com/reaatech/llm-cache - tags: llm, cache, semantic-cache, embeddings, openai, vector-search ## @reaatech/llm-cache-adapters-dynamodb **Category:** Observability & Cost · **Repo:** llm-cache · **Status:** published v0.1.0 A DynamoDB storage adapter for `@reaatech/llm-cache` that persists exact-match cache entries with native TTL, GSI-backed metadata queries, and batch operations chunked to AWS limits. Exports a `DynamoDBAdapter` class implementing the `StorageAdapter` interface from `@reaatech/llm-cache`. - npm: https://www.npmjs.com/package/@reaatech/llm-cache-adapters-dynamodb - detail: https://reaatech.com/products/observability-cost/llm-cache/packages/llm-cache-adapters-dynamodb - repo: https://github.com/reaatech/llm-cache - tags: llm-cache, dynamodb, aws, cache, adapter ## @reaatech/llm-cache-adapters-qdrant **Category:** Observability & Cost · **Repo:** llm-cache · **Status:** published v0.1.0 A Qdrant vector database adapter for `@reaatech/llm-cache` that implements the `VectorStorageAdapter` interface, providing HNSW approximate nearest neighbor search with metadata filtering and deterministic UUID-based point IDs. - npm: https://www.npmjs.com/package/@reaatech/llm-cache-adapters-qdrant - detail: https://reaatech.com/products/observability-cost/llm-cache/packages/llm-cache-adapters-qdrant - repo: https://github.com/reaatech/llm-cache - tags: llm-cache, qdrant, vector, semantic-search, adapter ## @reaatech/llm-cache-adapters-redis **Category:** Observability & Cost · **Repo:** llm-cache · **Status:** published v0.1.0 A Redis storage adapter for the `@reaatech/llm-cache` library that implements the `StorageAdapter` interface, providing exact-match cache operations with automatic TTL via `SETEX`, batch operations, and metadata queries using `SCAN`. - npm: https://www.npmjs.com/package/@reaatech/llm-cache-adapters-redis - detail: https://reaatech.com/products/observability-cost/llm-cache/packages/llm-cache-adapters-redis - repo: https://github.com/reaatech/llm-cache - tags: llm-cache, redis, cache, adapter ## @reaatech/llm-cache-cost-tracker **Category:** Observability & Cost · **Repo:** llm-cache · **Status:** published v0.1.0 A cost calculator and pricing database for LLM API usage, providing a `CostCalculator` class that computes per-request costs from token counts and model pricing, and tracks savings from cache hits. It ships with reference pricing for 40+ models across OpenAI, Anthropic, and Google, and implements the `CostCalculatorLike` interface for drop-in integration with `@reaatech/llm-cache`. - npm: https://www.npmjs.com/package/@reaatech/llm-cache-cost-tracker - detail: https://reaatech.com/products/observability-cost/llm-cache/packages/llm-cache-cost-tracker - repo: https://github.com/reaatech/llm-cache - tags: llm-cache, cost, pricing, openai, anthropic ## @reaatech/llm-cache-observability **Category:** Observability & Cost · **Repo:** llm-cache · **Status:** published v0.1.0 A structured JSON logger and Prometheus-compatible metrics collector for LLM cache operations, providing automatic PII redaction on 17 sensitive field names, correlation ID propagation via `child()`, and cardinality-protected counters and histograms with zero runtime dependencies. - npm: https://www.npmjs.com/package/@reaatech/llm-cache-observability - detail: https://reaatech.com/products/observability-cost/llm-cache/packages/llm-cache-observability - repo: https://github.com/reaatech/llm-cache - tags: llm-cache, metrics, logging, prometheus, observability ## @reaatech/llm-cache-server **Category:** Observability & Cost · **Repo:** llm-cache · **Status:** published v0.1.0 An HTTP server wrapper for llm-cache that exposes a REST API for cache operations, Prometheus metrics, and health endpoints, configurable via environment variables for storage (memory, Redis, DynamoDB) and vector search (memory, Qdrant) backends. Exports `createApp()` returning an `App` object with an `http.Server`, cache engine instance, and `shutdown()` method, plus a `main()` convenience function for direct CLI or programmatic use. - npm: https://www.npmjs.com/package/@reaatech/llm-cache-server - detail: https://reaatech.com/products/observability-cost/llm-cache/packages/llm-cache-server - repo: https://github.com/reaatech/llm-cache - tags: llm-cache, server, http, cache ## @reaatech/llm-cost-telemetry **Category:** Observability & Cost · **Repo:** llm-cost-telemetry · **Status:** published v0.2.0 Core types, Zod schemas, shared utilities, and configuration loaders that serve as the foundation for the `@reaatech/llm-cost-telemetry-*` ecosystem. It exports 40+ domain types (CostSpan, BudgetConfig, TelemetryContext, etc.), 35 Zod schemas for runtime validation, 25 utility functions (ID generation, time window math, cost calculation), and typed configuration loaders, with only `zod` as a runtime dependency. - npm: https://www.npmjs.com/package/@reaatech/llm-cost-telemetry - detail: https://reaatech.com/products/observability-cost/llm-cost-telemetry/packages/llm-cost-telemetry - repo: https://github.com/reaatech/llm-cost-telemetry ## @reaatech/llm-cost-telemetry-aggregation **Category:** Observability & Cost · **Repo:** llm-cost-telemetry · **Status:** published v0.1.1 A set of classes (`CostCollector`, `CostAggregator`, `BudgetManager`) for buffering, aggregating by tenant/feature/route/model, and enforcing per-tenant daily/monthly budgets with cascading alert thresholds on LLM cost telemetry spans. - npm: https://www.npmjs.com/package/@reaatech/llm-cost-telemetry-aggregation - detail: https://reaatech.com/products/observability-cost/llm-cost-telemetry/packages/llm-cost-telemetry-aggregation - repo: https://github.com/reaatech/llm-cost-telemetry ## @reaatech/llm-cost-telemetry-calculator **Category:** Observability & Cost · **Repo:** llm-cost-telemetry · **Status:** published v0.1.1 A function that calculates LLM API costs across OpenAI, Anthropic, and Google models, with built-in pricing tables, cache-aware pricing, token counting, and pre-call cost estimation. - npm: https://www.npmjs.com/package/@reaatech/llm-cost-telemetry-calculator - detail: https://reaatech.com/products/observability-cost/llm-cost-telemetry/packages/llm-cost-telemetry-calculator - repo: https://github.com/reaatech/llm-cost-telemetry ## @reaatech/llm-cost-telemetry-cli **Category:** Observability & Cost · **Repo:** llm-cost-telemetry · **Status:** published v0.2.0 A CLI tool that generates LLM cost reports, checks budget status, and triggers exports to observability platforms (CloudWatch, Cloud Monitoring, Phoenix/Loki) from JSON cost span files or stdin. - npm: https://www.npmjs.com/package/@reaatech/llm-cost-telemetry-cli - detail: https://reaatech.com/products/observability-cost/llm-cost-telemetry/packages/llm-cost-telemetry-cli - repo: https://github.com/reaatech/llm-cost-telemetry ## @reaatech/llm-cost-telemetry-exporters **Category:** Observability & Cost · **Repo:** llm-cost-telemetry · **Status:** published v0.1.1 Exporters for pushing LLM cost telemetry to AWS CloudWatch (standard and EMF), GCP Cloud Monitoring, and Grafana Loki/Phoenix, provided as configurable class instances (`CloudWatchExporter`, `CloudMonitoringExporter`, `PhoenixExporter`) that extend a shared `BaseExporter` with batching and retry logic. Requires the respective cloud SDKs (`@aws-sdk/client-cloudwatch`, `@google-cloud/monitoring`) as peer dependencies. - npm: https://www.npmjs.com/package/@reaatech/llm-cost-telemetry-exporters - detail: https://reaatech.com/products/observability-cost/llm-cost-telemetry/packages/llm-cost-telemetry-exporters - repo: https://github.com/reaatech/llm-cost-telemetry ## @reaatech/llm-cost-telemetry-mcp **Category:** Observability & Cost · **Repo:** llm-cost-telemetry · **Status:** published v0.1.1 An MCP server that exposes three layers of LLM cost telemetry tools — atomic span recording, multi-dimensional aggregation, and budget enforcement — consumable by MCP clients like Claude Desktop and Cursor. - npm: https://www.npmjs.com/package/@reaatech/llm-cost-telemetry-mcp - detail: https://reaatech.com/products/observability-cost/llm-cost-telemetry/packages/llm-cost-telemetry-mcp - repo: https://github.com/reaatech/llm-cost-telemetry ## @reaatech/llm-cost-telemetry-observability **Category:** Observability & Cost · **Repo:** llm-cost-telemetry · **Status:** published v0.1.1 A set of OpenTelemetry tracing, metrics, and Pino-based logging managers specifically for tracking LLM API costs, providing classes like `TracingManager`, `MetricsManager`, and a `getLogger()` singleton that automatically record token usage, cost amounts, and PII-redacted logs with Gen AI semantic conventions. - npm: https://www.npmjs.com/package/@reaatech/llm-cost-telemetry-observability - detail: https://reaatech.com/products/observability-cost/llm-cost-telemetry/packages/llm-cost-telemetry-observability - repo: https://github.com/reaatech/llm-cost-telemetry ## @reaatech/llm-cost-telemetry-providers **Category:** Observability & Cost · **Repo:** llm-cost-telemetry · **Status:** published v0.1.1 Provides `wrapOpenAI`, `wrapAnthropic`, and `wrapGoogleGenerativeAI` functions that wrap their respective official SDK clients to automatically emit `CostSpan` objects with token usage, timing, and telemetry context from every API call. - npm: https://www.npmjs.com/package/@reaatech/llm-cost-telemetry-providers - detail: https://reaatech.com/products/observability-cost/llm-cost-telemetry/packages/llm-cost-telemetry-providers - repo: https://github.com/reaatech/llm-cost-telemetry ## @reaatech/otel-cost-exporter **Category:** Observability & Cost · **Repo:** otel-cost-exporter · **Status:** published v0.1.0 An OpenTelemetry span processor that reads GenAI semantic convention spans, calculates real-time USD costs using bundled pricing tables for major LLM providers, and exports the cost metrics via Prometheus, OTLP, or JSON. - npm: https://www.npmjs.com/package/@reaatech/otel-cost-exporter - detail: https://reaatech.com/products/observability-cost/otel-cost-exporter/packages/otel-cost-exporter - repo: https://github.com/reaatech/otel-cost-exporter ## @reaatech/otel-cost-exporter-calculator **Category:** Observability & Cost · **Repo:** otel-cost-exporter · **Status:** published v0.1.0 A cost calculator that converts raw token counts from GenAI semantic convention spans into per-model cost breakdowns in USD, with model name normalization, provider detection, and LRU pricing caching. It provides a `CostCalculator` class (or `createCostCalculator` factory) that accepts a pricing provider, cache, normalizer, and optional default price, and returns a `CostResult` with input, output, and total costs. - npm: https://www.npmjs.com/package/@reaatech/otel-cost-exporter-calculator - detail: https://reaatech.com/products/observability-cost/otel-cost-exporter/packages/otel-cost-exporter-calculator - repo: https://github.com/reaatech/otel-cost-exporter ## @reaatech/otel-cost-exporter-cli **Category:** Observability & Cost · **Repo:** otel-cost-exporter · **Status:** published v0.1.0 A CLI that starts an OTLP collector service, validates pricing tables, generates cost reports from span data, and inspects configuration, providing commands like `serve`, `report`, `config`, and `validate`. - npm: https://www.npmjs.com/package/@reaatech/otel-cost-exporter-cli - detail: https://reaatech.com/products/observability-cost/otel-cost-exporter/packages/otel-cost-exporter-cli - repo: https://github.com/reaatech/otel-cost-exporter ## @reaatech/otel-cost-exporter-core **Category:** Observability & Cost · **Repo:** otel-cost-exporter · **Status:** published v0.1.0 Shared domain types, Zod schemas, GenAI semantic convention constants, and a Pino-based logger factory for the `@reaatech/otel-cost-exporter-*` ecosystem. Exports TypeScript types (`CostSpan`, `PriceEntry`, `CostBreakdown`), their Zod validation schemas, and utility functions like `parseIntervalMs()` and `createLogger()`. - npm: https://www.npmjs.com/package/@reaatech/otel-cost-exporter-core - detail: https://reaatech.com/products/observability-cost/otel-cost-exporter/packages/otel-cost-exporter-core - repo: https://github.com/reaatech/otel-cost-exporter ## @reaatech/otel-cost-exporter-pricing **Category:** Observability & Cost · **Repo:** otel-cost-exporter · **Status:** published v0.1.0 A pricing table loader and lookup utility that bundles pre-validated YAML pricing data for OpenAI, Anthropic, Google, AWS Bedrock, and Azure, providing `loadPricingData()` and `createPricingTable()` functions for exact and wildcard model price lookups with custom override support. - npm: https://www.npmjs.com/package/@reaatech/otel-cost-exporter-pricing - detail: https://reaatech.com/products/observability-cost/otel-cost-exporter/packages/otel-cost-exporter-pricing - repo: https://github.com/reaatech/otel-cost-exporter ## @reaatech/otel-genai-semconv-anthropic **Category:** Observability & Cost · **Repo:** otel-genai-semconv · **Status:** published v0.1.0 An OpenTelemetry instrumentation for the Anthropic Node.js SDK that wraps `client.messages.create()` to emit GenAI semantic convention spans with request metadata, token usage, cost tracking, and streaming metrics. - npm: https://www.npmjs.com/package/@reaatech/otel-genai-semconv-anthropic - detail: https://reaatech.com/products/observability-cost/otel-genai-semconv/packages/otel-genai-semconv-anthropic - repo: https://github.com/reaatech/otel-genai-semconv ## @reaatech/otel-genai-semconv-bedrock **Category:** Observability & Cost · **Repo:** otel-genai-semconv · **Status:** published v0.1.0 A zero-config OpenTelemetry instrumentation class for the AWS Bedrock Runtime SDK that wraps `client.send()` to emit GenAI semantic convention spans with model-family-aware attribute mapping for Anthropic Claude, Amazon Titan, Cohere Command, and AI21 Jurassic models. - npm: https://www.npmjs.com/package/@reaatech/otel-genai-semconv-bedrock - detail: https://reaatech.com/products/observability-cost/otel-genai-semconv/packages/otel-genai-semconv-bedrock - repo: https://github.com/reaatech/otel-genai-semconv ## @reaatech/otel-genai-semconv-core **Category:** Observability & Cost · **Repo:** otel-genai-semconv · **Status:** published v0.1.0 Canonical TypeScript types, constants, Zod schemas, and span-builder utilities for the OpenTelemetry GenAI semantic conventions, providing the single source of truth for all `gen_ai.*` attribute names, event types, error classifications, and domain models used across the `@reaatech/otel-genai-semconv-*` ecosystem. It exports typed constants, interfaces like `LLMRequest` and `LLMResponse`, Zod validation schemas, and a `SpanBuilder` class that constructs OTel-compliant spans with automatic attribute mapping, requiring only `zod` and `@opentelemetry/api` at runtime. - npm: https://www.npmjs.com/package/@reaatech/otel-genai-semconv-core - detail: https://reaatech.com/products/observability-cost/otel-genai-semconv/packages/otel-genai-semconv-core - repo: https://github.com/reaatech/otel-genai-semconv ## @reaatech/otel-genai-semconv-exporters **Category:** Observability & Cost · **Repo:** otel-genai-semconv · **Status:** published v0.1.0 Custom OpenTelemetry span exporters that convert GenAI spans into the native formats of Arize Phoenix, Langfuse, and Google Cloud Trace, each implementing the `SpanExporter` interface with a `get*Format()` method for direct format conversion. - npm: https://www.npmjs.com/package/@reaatech/otel-genai-semconv-exporters - detail: https://reaatech.com/products/observability-cost/otel-genai-semconv/packages/otel-genai-semconv-exporters - repo: https://github.com/reaatech/otel-genai-semconv ## @reaatech/otel-genai-semconv-instrumentation **Category:** Observability & Cost · **Repo:** otel-genai-semconv · **Status:** published v0.1.0 Provides tracer management, lifecycle hooks, streaming response handling, error classification, retry with exponential backoff, per-provider circuit breaking, chunk aggregation, and span-level PII redaction as a set of classes (`TracerManager`, `HookManager`, `ErrorHandler`, `RetryHandler`, `CircuitBreaker`) for instrumenting LLM calls with OpenTelemetry. - npm: https://www.npmjs.com/package/@reaatech/otel-genai-semconv-instrumentation - detail: https://reaatech.com/products/observability-cost/otel-genai-semconv/packages/otel-genai-semconv-instrumentation - repo: https://github.com/reaatech/otel-genai-semconv ## @reaatech/otel-genai-semconv-observability **Category:** Observability & Cost · **Repo:** otel-genai-semconv · **Status:** published v0.1.0 A zero-config observability kit for GenAI workloads, providing structured Pino logging, OpenTelemetry SDK initialization with OTLP trace export, pre-built metrics counters/histograms for LLM requests, tokens, cost, errors, and TTFT, plus runtime health checks with a pluggable HTTP endpoint. Exports functions (`initOTelSDK`, `createLogger`, `initMetrics`, `logGenAIEvent`, etc.) that bundle Pino v10 and the OpenTelemetry JS SDK. - npm: https://www.npmjs.com/package/@reaatech/otel-genai-semconv-observability - detail: https://reaatech.com/products/observability-cost/otel-genai-semconv/packages/otel-genai-semconv-observability - repo: https://github.com/reaatech/otel-genai-semconv ## @reaatech/otel-genai-semconv-openai **Category:** Observability & Cost · **Repo:** otel-genai-semconv · **Status:** published v0.1.0 A function `instrument(client)` that wraps an OpenAI SDK client instance to automatically emit OpenTelemetry GenAI semantic convention spans for every `chat.completions.create()` call, capturing request metadata, token usage, cost, and streaming metrics. - npm: https://www.npmjs.com/package/@reaatech/otel-genai-semconv-openai - detail: https://reaatech.com/products/observability-cost/otel-genai-semconv/packages/otel-genai-semconv-openai - repo: https://github.com/reaatech/otel-genai-semconv ## @reaatech/otel-genai-semconv-utils **Category:** Observability & Cost · **Repo:** otel-genai-semconv · **Status:** published v0.1.0 Token counting, cost calculation, and PII redaction utilities for LLM observability. Provides a `TokenCounter` class with tiktoken-based estimation for OpenAI models and character-based fallbacks for Anthropic, Vertex AI, and Bedrock; a `CostCalculator` class with built-in pricing tables for GPT-4, GPT-4o, Claude 3, Gemini, and Bedrock model families; and a `PIIRedactor` class that recursively redacts emails, SSNs, credit cards, IP addresses, and phone numbers from nested objects. - npm: https://www.npmjs.com/package/@reaatech/otel-genai-semconv-utils - detail: https://reaatech.com/products/observability-cost/otel-genai-semconv/packages/otel-genai-semconv-utils - repo: https://github.com/reaatech/otel-genai-semconv ## @reaatech/otel-genai-semconv-vertexai **Category:** Observability & Cost · **Repo:** otel-genai-semconv · **Status:** published v0.1.0 A function that wraps a Google Generative Language (Vertex AI) SDK model instance to automatically emit OpenTelemetry GenAI semantic convention spans on every `generateContent()` call, including GCP metadata, generation config attributes, candidate events, and optional cost tracking. - npm: https://www.npmjs.com/package/@reaatech/otel-genai-semconv-vertexai - detail: https://reaatech.com/products/observability-cost/otel-genai-semconv/packages/otel-genai-semconv-vertexai - repo: https://github.com/reaatech/otel-genai-semconv # Orchestration & Protocols > 38 packages — Agent mesh, confidence routing, handoff protocols, A2A. ## @reaatech/a2a-reference-auth **Category:** Orchestration & Protocols · **Repo:** a2a-reference-ts · **Status:** published v0.2.0 Pluggable authentication and authorization strategies for A2A agents, providing `NoneStrategy`, `ApiKeyStrategy`, `JwtStrategy`, and `OAuth2Strategy` classes plus a `extractScopes` utility function. Designed for use with the A2A agent framework. - npm: https://www.npmjs.com/package/@reaatech/a2a-reference-auth - detail: https://reaatech.com/products/orchestration-protocols/a2a-reference-ts/packages/a2a-reference-auth - repo: https://github.com/reaatech/a2a-reference-ts ## @reaatech/a2a-reference-cli **Category:** Orchestration & Protocols · **Repo:** a2a-reference-ts · **Status:** published v0.2.0 Description pending. - npm: https://www.npmjs.com/package/@reaatech/a2a-reference-cli - detail: https://reaatech.com/products/orchestration-protocols/a2a-reference-ts/packages/a2a-reference-cli - repo: https://github.com/reaatech/a2a-reference-ts ## @reaatech/a2a-reference-client **Category:** Orchestration & Protocols · **Repo:** a2a-reference-ts · **Status:** published v0.1.1 A type-safe A2A client SDK that provides a class (`A2AClient`) for task submission, agent discovery, and SSE streaming against A2A-compatible servers. It handles agent card caching, retries with exponential backoff, and supports both synchronous task management and async event streaming via `sendSubscribe`. - npm: https://www.npmjs.com/package/@reaatech/a2a-reference-client - detail: https://reaatech.com/products/orchestration-protocols/a2a-reference-ts/packages/a2a-reference-client - repo: https://github.com/reaatech/a2a-reference-ts ## @reaatech/a2a-reference-core **Category:** Orchestration & Protocols · **Repo:** a2a-reference-ts · **Status:** published v0.2.0 Zod schemas, TypeScript types, error classes, and a signature verification function for the A2A (Agent-to-Agent) protocol, providing canonical validation and parsing for task lifecycle messages, agent cards, and security schemes. - npm: https://www.npmjs.com/package/@reaatech/a2a-reference-core - detail: https://reaatech.com/products/orchestration-protocols/a2a-reference-ts/packages/a2a-reference-core - repo: https://github.com/reaatech/a2a-reference-ts ## @reaatech/a2a-reference-mcp-bridge **Category:** Orchestration & Protocols · **Repo:** a2a-reference-ts · **Status:** published v0.1.2 A bidirectional protocol adapter that exposes MCP tools as A2A skills via `McpToolAdapter` (producing an enriched Agent Card), and wraps an A2A agent as an MCP server via `A2aAsMcpServer` (starting a stdio or SSE transport). - npm: https://www.npmjs.com/package/@reaatech/a2a-reference-mcp-bridge - detail: https://reaatech.com/products/orchestration-protocols/a2a-reference-ts/packages/a2a-reference-mcp-bridge - repo: https://github.com/reaatech/a2a-reference-ts ## @reaatech/a2a-reference-observability **Category:** Orchestration & Protocols · **Repo:** a2a-reference-ts · **Status:** published v0.2.0 Pino-based structured logging with correlation IDs and OpenTelemetry abstractions (tracers, meters, spans) for A2A agents, providing `createLogger`, `withCorrelationId`, `getTracer`, `getMeter`, and `withTaskSpan` functions with no-op defaults that can be replaced by a custom `TelemetryProvider`. - npm: https://www.npmjs.com/package/@reaatech/a2a-reference-observability - detail: https://reaatech.com/products/orchestration-protocols/a2a-reference-ts/packages/a2a-reference-observability - repo: https://github.com/reaatech/a2a-reference-ts ## @reaatech/a2a-reference-persistence **Category:** Orchestration & Protocols · **Repo:** a2a-reference-ts · **Status:** published v0.2.0 Provides in-memory, filesystem, Redis, and Postgres implementations of a `TaskStore` interface for persisting A2A (Agent-to-Agent) tasks, each exposed as a class constructor. - npm: https://www.npmjs.com/package/@reaatech/a2a-reference-persistence - detail: https://reaatech.com/products/orchestration-protocols/a2a-reference-ts/packages/a2a-reference-persistence - repo: https://github.com/reaatech/a2a-reference-ts ## @reaatech/a2a-reference-server **Category:** Orchestration & Protocols · **Repo:** a2a-reference-ts · **Status:** published v0.2.0 A server framework that implements the A2A (Agent-to-Agent) protocol, providing Express 5 and Hono adapters that expose JSON-RPC 2.0 endpoints, SSE streaming, health checks, rate limiting, and push notifications for agent communication. - npm: https://www.npmjs.com/package/@reaatech/a2a-reference-server - detail: https://reaatech.com/products/orchestration-protocols/a2a-reference-ts/packages/a2a-reference-server - repo: https://github.com/reaatech/a2a-reference-ts ## @reaatech/agent-handoff **Category:** Orchestration & Protocols · **Repo:** agent-handoff-protocol · **Status:** published v0.1.0 Core types, utilities, and configuration for the Agent Handoff Protocol, providing 35+ TypeScript types, 7 typed error classes, a typed event emitter, a retry utility with configurable backoff, and a config factory — all with zero runtime dependencies. - npm: https://www.npmjs.com/package/@reaatech/agent-handoff - detail: https://reaatech.com/products/orchestration-protocols/agent-handoff-protocol/packages/agent-handoff - repo: https://github.com/reaatech/agent-handoff-protocol ## @reaatech/agent-handoff-compression **Category:** Orchestration & Protocols · **Repo:** agent-handoff-protocol · **Status:** published v0.1.0 Compresses conversation history before agent handoff using three built-in strategies (hybrid, summary, sliding-window) with configurable token budgets. Exports compressor classes (`HybridCompressor`, `SummaryCompressor`, `SlidingWindowCompressor`) that implement the `ContextCompressor` interface from `@reaatech/agent-handoff`, plus a `SimpleTokenCounter` for heuristic token estimation. - npm: https://www.npmjs.com/package/@reaatech/agent-handoff-compression - detail: https://reaatech.com/products/orchestration-protocols/agent-handoff-protocol/packages/agent-handoff-compression - repo: https://github.com/reaatech/agent-handoff-protocol ## @reaatech/agent-handoff-protocol **Category:** Orchestration & Protocols · **Repo:** agent-handoff-protocol · **Status:** published v0.1.0 A TypeScript library for transferring a conversation from one AI agent to another mid-session, providing context compression, capability-based routing, payload validation, transport delivery, and rejection handling with fallback. It exports a `HandoffManager` class that orchestrates the lifecycle, along with composable components like `HybridCompressor`, `CapabilityBasedRouter`, and `MCPTransport`. - npm: https://www.npmjs.com/package/@reaatech/agent-handoff-protocol - detail: https://reaatech.com/products/orchestration-protocols/agent-handoff-protocol/packages/agent-handoff-protocol - repo: https://github.com/reaatech/agent-handoff-protocol ## @reaatech/agent-handoff-routing **Category:** Orchestration & Protocols · **Repo:** agent-handoff-protocol · **Status:** published v0.1.0 A weighted scoring engine that selects the best target agent during a handoff, implementing a route/clarify/fallback decision tree with an in-memory agent registry. Exports `CapabilityBasedRouter` (a class implementing the `HandoffRouter` interface from `@reaatech/agent-handoff`) and `AgentRegistry`. - npm: https://www.npmjs.com/package/@reaatech/agent-handoff-routing - detail: https://reaatech.com/products/orchestration-protocols/agent-handoff-protocol/packages/agent-handoff-routing - repo: https://github.com/reaatech/agent-handoff-protocol ## @reaatech/agent-handoff-transport **Category:** Orchestration & Protocols · **Repo:** agent-handoff-protocol · **Status:** published v0.1.0 Transport layer implementations for delivering handoffs between agents, providing MCP (tool-call-based), A2A (HTTP POST with retry), and a transport factory with health-check caching and priority-based auto-selection. Exports `MCPTransport`, `A2ATransport`, and `TransportFactory` classes. - npm: https://www.npmjs.com/package/@reaatech/agent-handoff-transport - detail: https://reaatech.com/products/orchestration-protocols/agent-handoff-protocol/packages/agent-handoff-transport - repo: https://github.com/reaatech/agent-handoff-protocol ## @reaatech/agent-handoff-validation **Category:** Orchestration & Protocols · **Repo:** agent-handoff-protocol · **Status:** published v0.1.0 Validates `HandoffPayload` structure and checks agent compatibility (language, capacity, availability, history size) for the Agent Handoff Protocol. Exports a `HandoffValidator` class with a `validatePayload` method, plus standalone manual validation functions and a `classifyRejectionReason` utility; optionally uses Zod for stricter schema validation when installed. - npm: https://www.npmjs.com/package/@reaatech/agent-handoff-validation - detail: https://reaatech.com/products/orchestration-protocols/agent-handoff-protocol/packages/agent-handoff-validation - repo: https://github.com/reaatech/agent-handoff-protocol ## @reaatech/agent-mesh **Category:** Orchestration & Protocols · **Repo:** agent-mesh · **Status:** published v1.2.0 A Zod-schema and TypeScript type package that defines the core domain entities, request/response shapes, and environment configuration for the agent-mesh multi-agent orchestrator ecosystem. It exports 15+ validated schemas and types (e.g., `IncomingRequestSchema`, `ContextPacketSchema`, `CircuitBreakerStateSchema`) along with shared constants, with `zod` as its only runtime dependency. - npm: https://www.npmjs.com/package/@reaatech/agent-mesh - detail: https://reaatech.com/products/orchestration-protocols/agent-mesh/packages/agent-mesh - repo: https://github.com/reaatech/agent-mesh ## @reaatech/agent-mesh-classifier **Category:** Orchestration & Protocols · **Repo:** agent-mesh · **Status:** published v1.1.1 A Gemini Flash intent classifier that maps user requests to registered agents, returning a `ClassifierOutput` with agent ID, confidence score, and detected language. It dynamically builds prompts from an agent registry and falls back to a keyword-based mock classifier when Gemini is unavailable. - npm: https://www.npmjs.com/package/@reaatech/agent-mesh-classifier - detail: https://reaatech.com/products/orchestration-protocols/agent-mesh/packages/agent-mesh-classifier - repo: https://github.com/reaatech/agent-mesh ## @reaatech/agent-mesh-confidence **Category:** Orchestration & Protocols · **Repo:** agent-mesh · **Status:** published v1.0.2 A decision engine that evaluates classifier output against agent thresholds using a 5-rule decision tree to route requests, ask for clarification, or fall back to a default agent. It exports `evaluateConfidenceGate` (the main routing function), `generateClarificationQuestion`, and a singleton `clarificationCache` with LRU/TTL semantics, and is designed to work with the agent-mesh orchestrator's agent registry. - npm: https://www.npmjs.com/package/@reaatech/agent-mesh-confidence - detail: https://reaatech.com/products/orchestration-protocols/agent-mesh/packages/agent-mesh-confidence - repo: https://github.com/reaatech/agent-mesh ## @reaatech/agent-mesh-gateway **Category:** Orchestration & Protocols · **Repo:** agent-mesh · **Status:** published v1.0.2 An Express middleware pipeline that provides a `/v1/request` endpoint for orchestrating agent dispatch, including authentication, rate limiting, TLS enforcement, health checks, and Slack profile resolution. - npm: https://www.npmjs.com/package/@reaatech/agent-mesh-gateway - detail: https://reaatech.com/products/orchestration-protocols/agent-mesh/packages/agent-mesh-gateway - repo: https://github.com/reaatech/agent-mesh ## @reaatech/agent-mesh-mcp-server **Category:** Orchestration & Protocols · **Repo:** agent-mesh · **Status:** published v1.0.2 Exposes the agent-mesh orchestrator as an MCP-compliant agent by providing Express middleware (`mcpMiddleware`), JSON-RPC 2.0 handlers, and SSE transport for legacy client compatibility. Depends on `@reaatech/agent-mesh` and Express at runtime. - npm: https://www.npmjs.com/package/@reaatech/agent-mesh-mcp-server - detail: https://reaatech.com/products/orchestration-protocols/agent-mesh/packages/agent-mesh-mcp-server - repo: https://github.com/reaatech/agent-mesh ## @reaatech/agent-mesh-observability **Category:** Orchestration & Protocols · **Repo:** agent-mesh · **Status:** published v1.0.2 A structured observability layer for the agent-mesh orchestrator, providing Winston-powered JSON logging with automatic PII redaction, OpenTelemetry tracing and metrics (histograms, counters), and audit event logging for compliance. Exports a default `logger`, a `createChildLogger` factory for request-scoped context, and metric recording functions like `recordSessionLookupDuration` and `recordAgentDispatchDuration`. - npm: https://www.npmjs.com/package/@reaatech/agent-mesh-observability - detail: https://reaatech.com/products/orchestration-protocols/agent-mesh/packages/agent-mesh-observability - repo: https://github.com/reaatech/agent-mesh ## @reaatech/agent-mesh-postgres **Category:** Orchestration & Protocols · **Repo:** agent-mesh · **Status:** published v0.2.0 Description pending. - npm: https://www.npmjs.com/package/@reaatech/agent-mesh-postgres - detail: https://reaatech.com/products/orchestration-protocols/agent-mesh/packages/agent-mesh-postgres - repo: https://github.com/reaatech/agent-mesh ## @reaatech/agent-mesh-redis **Category:** Orchestration & Protocols · **Repo:** agent-mesh · **Status:** published v0.2.0 Description pending. - npm: https://www.npmjs.com/package/@reaatech/agent-mesh-redis - detail: https://reaatech.com/products/orchestration-protocols/agent-mesh/packages/agent-mesh-redis - repo: https://github.com/reaatech/agent-mesh ## @reaatech/agent-mesh-registry **Category:** Orchestration & Protocols · **Repo:** agent-mesh · **Status:** published v1.0.2 A YAML-based agent registry loader that parses, validates (with Zod), and hot-reloads agent configurations via SIGHUP, exposing a thread-safe singleton with atomic-swap semantics and SSRF-safe URL validation. - npm: https://www.npmjs.com/package/@reaatech/agent-mesh-registry - detail: https://reaatech.com/products/orchestration-protocols/agent-mesh/packages/agent-mesh-registry - repo: https://github.com/reaatech/agent-mesh ## @reaatech/agent-mesh-router **Category:** Orchestration & Protocols · **Repo:** agent-mesh · **Status:** published v1.1.0 A Zod-validated MCP dispatch layer that routes requests to registered agents via StreamableHTTP transport, managing connection pooling, circuit breakers, retries, and timeouts per agent. Exports `dispatchToAgent` as the main entry point, along with turn-history helpers and a singleton MCP client factory. - npm: https://www.npmjs.com/package/@reaatech/agent-mesh-router - detail: https://reaatech.com/products/orchestration-protocols/agent-mesh/packages/agent-mesh-router - repo: https://github.com/reaatech/agent-mesh ## @reaatech/agent-mesh-session **Category:** Orchestration & Protocols · **Repo:** agent-mesh · **Status:** published v1.1.1 Firestore-backed session management for the agent-mesh orchestrator, providing functions (`createSession`, `getActiveSession`, `appendTurn`, `closeSession`, `resumeSession`) to create, persist, and resume multi-turn conversation state with sliding TTL, turn history, and workflow state passthrough. - npm: https://www.npmjs.com/package/@reaatech/agent-mesh-session - detail: https://reaatech.com/products/orchestration-protocols/agent-mesh/packages/agent-mesh-session - repo: https://github.com/reaatech/agent-mesh ## @reaatech/agent-mesh-utils **Category:** Orchestration & Protocols · **Repo:** agent-mesh · **Status:** published v1.1.1 A per-agent circuit breaker with Firestore-backed persistence and leader-elected cross-instance state synchronization, exposed as a singleton object with synchronous methods (`canCall`, `recordSuccess`, `recordFailure`) plus async persistence lifecycle functions (`startCircuitBreakerPersistence`, `stopCircuitBreakerPersistence`). Depends on Firestore at runtime for distributed state coordination across Cloud Run instances. - npm: https://www.npmjs.com/package/@reaatech/agent-mesh-utils - detail: https://reaatech.com/products/orchestration-protocols/agent-mesh/packages/agent-mesh-utils - repo: https://github.com/reaatech/agent-mesh ## @reaatech/confidence-router **Category:** Orchestration & Protocols · **Repo:** confidence-router · **Status:** published v0.1.1 A threshold-based decision engine that takes a classification result with confidence scores and returns a `RoutingDecision` indicating whether to **route** (high confidence), **clarify** (ambiguous), or **fallback** (low confidence). - npm: https://www.npmjs.com/package/@reaatech/confidence-router - detail: https://reaatech.com/products/orchestration-protocols/confidence-router/packages/confidence-router - repo: https://github.com/reaatech/confidence-router ## @reaatech/confidence-router-classifiers **Category:** Orchestration & Protocols · **Repo:** confidence-router · **Status:** published v0.1.1 A pluggable classifier system for confidence-router, providing keyword matching, embedding similarity, and LLM-based classification as classes conforming to the `Classifier` interface, with a `ClassifierRegistry` for named registration and automatic fallback chains. - npm: https://www.npmjs.com/package/@reaatech/confidence-router-classifiers - detail: https://reaatech.com/products/orchestration-protocols/confidence-router/packages/confidence-router-classifiers - repo: https://github.com/reaatech/confidence-router ## @reaatech/confidence-router-core **Category:** Orchestration & Protocols · **Repo:** confidence-router · **Status:** published v0.1.1 Core type definitions, error classes, configuration utilities, and the `DecisionEngine` for the confidence-router ecosystem. Exports TypeScript types (`Prediction`, `RoutingDecision`, `RouterConfig`, `Classifier` interface), a `RouterError` class with enumerated error types, a `DecisionEngine` class that evaluates confidence scores against route/clarify/fallback thresholds, and configuration helpers (`DEFAULT_CONFIG`, `validateConfig`, `mergeConfig`). Zero runtime dependencies. - npm: https://www.npmjs.com/package/@reaatech/confidence-router-core - detail: https://reaatech.com/products/orchestration-protocols/confidence-router/packages/confidence-router-core - repo: https://github.com/reaatech/confidence-router ## @reaatech/confidence-router-evaluation **Category:** Orchestration & Protocols · **Repo:** confidence-router · **Status:** published v0.1.1 A grid search optimizer that tunes `routeThreshold` and `fallbackThreshold` on any `RouterInterface` object to maximize F1 score against a labeled dataset, returning `OptimizedThresholds` with the best thresholds and full `EvaluationMetrics`. - npm: https://www.npmjs.com/package/@reaatech/confidence-router-evaluation - detail: https://reaatech.com/products/orchestration-protocols/confidence-router/packages/confidence-router-evaluation - repo: https://github.com/reaatech/confidence-router ## @reaatech/confidence-router-languages **Category:** Orchestration & Protocols · **Repo:** confidence-router · **Status:** published v0.1.1 Provides locale-aware clarification prompt generation for confidence-router, exposing `LanguageManager` and `PromptGenerator` classes that handle 47 built-in languages with RTL support, list separators, and conjunctions, falling back to English for unknown codes. - npm: https://www.npmjs.com/package/@reaatech/confidence-router-languages - detail: https://reaatech.com/products/orchestration-protocols/confidence-router/packages/confidence-router-languages - repo: https://github.com/reaatech/confidence-router ## @reaatech/llm-router-cli **Category:** Orchestration & Protocols · **Repo:** llm-router · **Status:** published v1.0.1 A CLI that provides four commands—`route`, `benchmark`, `cost-report`, and `validate-config`—for routing prompts through configurable LLM strategies, benchmarking model performance with latency and cost statistics, generating cost summaries per budget period, and validating router configuration files. - npm: https://www.npmjs.com/package/@reaatech/llm-router-cli - detail: https://reaatech.com/products/orchestration-protocols/llm-router/packages/llm-router-cli - repo: https://github.com/reaatech/llm-router ## @reaatech/llm-router-core **Category:** Orchestration & Protocols · **Repo:** llm-router · **Status:** published v1.0.0 Core TypeScript types, Zod schemas, and input validation for the llm-router ecosystem, providing 30+ domain types and 11 runtime validation schemas for model definitions, routing requests, configurations, budgets, quality scores, and cost telemetry. Exports composable enums, circuit breaker types, and dual ESM/CJS modules with zero runtime dependencies beyond `zod`. - npm: https://www.npmjs.com/package/@reaatech/llm-router-core - detail: https://reaatech.com/products/orchestration-protocols/llm-router/packages/llm-router-core - repo: https://github.com/reaatech/llm-router ## @reaatech/llm-router-engine **Category:** Orchestration & Protocols · **Repo:** llm-router · **Status:** published v1.0.1 A config-driven `LLMRouter` class that orchestrates model selection, fallback chains, cost tracking, A/B testing, quality scoring, and observability into a single routing decision for LLM calls. It requires an `executeModel` callback or registered provider clients to actually dispatch requests. - npm: https://www.npmjs.com/package/@reaatech/llm-router-engine - detail: https://reaatech.com/products/orchestration-protocols/llm-router/packages/llm-router-engine - repo: https://github.com/reaatech/llm-router ## @reaatech/llm-router-fallback **Category:** Orchestration & Protocols · **Repo:** llm-router · **Status:** published v1.0.0 A function that creates ordered fallback chains for LLM calls, with per-model circuit breakers and exponential-backoff retry logic, returning a `FallbackChain` instance whose `executeFrom` method automatically tries the next model when one fails. - npm: https://www.npmjs.com/package/@reaatech/llm-router-fallback - detail: https://reaatech.com/products/orchestration-protocols/llm-router/packages/llm-router-fallback - repo: https://github.com/reaatech/llm-router ## @reaatech/llm-router-mcp **Category:** Orchestration & Protocols · **Repo:** llm-router · **Status:** published v1.0.0 An MCP server that exposes three tools—`route_request`, `get_model_info`, and `get_cost_report`—for routing LLM requests through a pluggable router implementation via the Model Context Protocol. It provides a `createMCPServer` factory function that returns an `MCPServer` class instance, which requires a `RouterInterface` implementation and auto-detects stdio or Streamable HTTP transport. - npm: https://www.npmjs.com/package/@reaatech/llm-router-mcp - detail: https://reaatech.com/products/orchestration-protocols/llm-router/packages/llm-router-mcp - repo: https://github.com/reaatech/llm-router ## @reaatech/llm-router-strategies **Category:** Orchestration & Protocols · **Repo:** llm-router · **Status:** published v1.0.0 A set of pluggable routing strategies (CostOptimized, LatencyOptimized, JudgmentBased, CapabilityBased) and a priority-based `StrategyOrchestrator` that evaluates them in order to select the best LLM model for each request based on cost, latency, or capability constraints. - npm: https://www.npmjs.com/package/@reaatech/llm-router-strategies - detail: https://reaatech.com/products/orchestration-protocols/llm-router/packages/llm-router-strategies - repo: https://github.com/reaatech/llm-router ## @reaatech/llm-router-telemetry **Category:** Orchestration & Protocols · **Repo:** llm-router · **Status:** published v1.0.0 A set of classes (`CostTracker`, `BudgetManager`, `CostReporter`) and a `MetricsCollector` facade for tracking per-request LLM costs, enforcing daily budget limits with configurable soft/hard enforcement and alert callbacks, and exposing OpenTelemetry-compatible metrics. Designed to pair with `@reaatech/llm-router` but usable standalone. - npm: https://www.npmjs.com/package/@reaatech/llm-router-telemetry - detail: https://reaatech.com/products/orchestration-protocols/llm-router/packages/llm-router-telemetry - repo: https://github.com/reaatech/llm-router # MCP Infrastructure > 34 packages — Gateway, catalog, doctor, schema evolution, server starter, multi-tenancy. ## @reaatech/mcp-catalog-shared **Category:** MCP Infrastructure · **Repo:** mcp-catalog · **Status:** published v1.0.0 Shared TypeScript type definitions and Zod validation schemas for MCP Catalog domain entities (`Server`, `Capability`, `Tool`, `Resource`, `User`, `ApiKey`, `AccessPolicy`, `HealthCheck`, `AuditLog`) and their create/update/search operations. This types-only module depends solely on `zod` and provides canonical interfaces and runtime validation schemas for type-safe consumption and production of MCP Catalog domain objects. - npm: https://www.npmjs.com/package/@reaatech/mcp-catalog-shared - detail: https://reaatech.com/products/mcp-infrastructure/mcp-catalog/packages/mcp-catalog-shared - repo: https://github.com/reaatech/mcp-catalog ## @reaatech/mcp-gateway-allowlist **Category:** MCP Infrastructure · **Repo:** mcp-gateway · **Status:** published v1.1.0 Per-tenant tool access control for MCP gateways, providing Express middleware that enforces allow/deny lists with wildcard pattern matching and versioned allowlist storage. - npm: https://www.npmjs.com/package/@reaatech/mcp-gateway-allowlist - detail: https://reaatech.com/products/mcp-infrastructure/mcp-gateway/packages/mcp-gateway-allowlist - repo: https://github.com/reaatech/mcp-gateway ## @reaatech/mcp-gateway-audit **Category:** MCP Infrastructure · **Repo:** mcp-gateway · **Status:** published v1.1.0 A structured audit logging library for the MCP Gateway that captures security-relevant events with configurable severity, multiple storage backends (console, file, in-memory), tamper-evident SHA-256 chaining, and a query API. Provides logger classes and event creation utilities for compliance audit trails. - npm: https://www.npmjs.com/package/@reaatech/mcp-gateway-audit - detail: https://reaatech.com/products/mcp-infrastructure/mcp-gateway/packages/mcp-gateway-audit - repo: https://github.com/reaatech/mcp-gateway ## @reaatech/mcp-gateway-auth **Category:** MCP Infrastructure · **Repo:** mcp-gateway · **Status:** published v1.1.0 Pluggable Express middleware that authenticates requests via API key, JWT (with JWKS), OAuth2 token introspection (RFC 7662), or OIDC ID token validation, attaching a typed `AuthContext` with tenant, user, and scope information to the request object. - npm: https://www.npmjs.com/package/@reaatech/mcp-gateway-auth - detail: https://reaatech.com/products/mcp-infrastructure/mcp-gateway/packages/mcp-gateway-auth - repo: https://github.com/reaatech/mcp-gateway ## @reaatech/mcp-gateway-cache **Category:** MCP Infrastructure · **Repo:** mcp-gateway · **Status:** published v1.1.0 A cache manager for MCP Gateway responses, providing in-memory LRU or Redis backends with per-tool TTL strategies, `Cache-Control` bypass support, and standard `X-Cache` headers, exposed as a class (`CacheManager`) and an Express middleware function. - npm: https://www.npmjs.com/package/@reaatech/mcp-gateway-cache - detail: https://reaatech.com/products/mcp-infrastructure/mcp-gateway/packages/mcp-gateway-cache - repo: https://github.com/reaatech/mcp-gateway ## @reaatech/mcp-gateway-core **Category:** MCP Infrastructure · **Repo:** mcp-gateway · **Status:** published v1.1.0 Core types, Zod schemas, configuration loading, and structured logging for the MCP Gateway ecosystem. It provides domain interfaces, runtime validation, YAML-based config loading with hot-reload, SSRF-protected upstream validation, and a Pino-based structured logger. - npm: https://www.npmjs.com/package/@reaatech/mcp-gateway-core - detail: https://reaatech.com/products/mcp-infrastructure/mcp-gateway/packages/mcp-gateway-core - repo: https://github.com/reaatech/mcp-gateway ## @reaatech/mcp-gateway-fanout **Category:** MCP Infrastructure · **Repo:** mcp-gateway · **Status:** published v1.0.1 A function that fans out a single MCP request to multiple upstream servers, then aggregates responses using strategies like first-success, all-wait, or majority-vote. It provides `executeFanout()` and related utilities for weighted upstream selection, circuit breaking, retry with exponential backoff, and health checking. - npm: https://www.npmjs.com/package/@reaatech/mcp-gateway-fanout - detail: https://reaatech.com/products/mcp-infrastructure/mcp-gateway/packages/mcp-gateway-fanout - repo: https://github.com/reaatech/mcp-gateway ## @reaatech/mcp-gateway-gateway **Category:** MCP Infrastructure · **Repo:** mcp-gateway · **Status:** published v1.0.1 An Express 5-based MCP Gateway server factory (`createApp()`) that wires together authentication, rate limiting, schema validation, tool allowlists, fan-out routing, response caching, audit logging, and OpenTelemetry observability into a single middleware pipeline, with a CLI binary for start, health checks, config validation, and diagnostics. - npm: https://www.npmjs.com/package/@reaatech/mcp-gateway-gateway - detail: https://reaatech.com/products/mcp-infrastructure/mcp-gateway/packages/mcp-gateway-gateway - repo: https://github.com/reaatech/mcp-gateway ## @reaatech/mcp-gateway-observability **Category:** MCP Infrastructure · **Repo:** mcp-gateway · **Status:** published v1.0.1 OpenTelemetry tracing, metrics, health checks, and structured logging for the MCP Gateway, providing auto-configured OTel SDK initialization, pre-built gateway metrics (counters, histograms, gauges), liveness/readiness/deep-health endpoints, and structured JSON logging via Pino. Exports health check functions (`getLiveness`, `getDeepHealth`, `registerProbe`, `createRedisProbe`), metric instruments, and a Pino logger. - npm: https://www.npmjs.com/package/@reaatech/mcp-gateway-observability - detail: https://reaatech.com/products/mcp-infrastructure/mcp-gateway/packages/mcp-gateway-observability - repo: https://github.com/reaatech/mcp-gateway ## @reaatech/mcp-gateway-rate-limit **Category:** MCP Infrastructure · **Repo:** mcp-gateway · **Status:** published v1.1.2 A per-tenant rate limiter for MCP gateways using a token bucket algorithm, providing Express middleware that enforces configurable per-minute and per-day limits with standard `X-RateLimit-*` headers and JSON-RPC 429 error responses. Exports `createRateLimiter()` factory (returns a `RateLimiter` class instance) and `createRateLimitMiddleware()` for Express, with optional Redis-backed storage via atomic Lua scripts. - npm: https://www.npmjs.com/package/@reaatech/mcp-gateway-rate-limit - detail: https://reaatech.com/products/mcp-infrastructure/mcp-gateway/packages/mcp-gateway-rate-limit - repo: https://github.com/reaatech/mcp-gateway ## @reaatech/mcp-gateway-validation **Category:** MCP Infrastructure · **Repo:** mcp-gateway · **Status:** published v1.0.1 JSON Schema validation for MCP protocol messages, providing an Express middleware that validates JSON-RPC 2.0 request structure and MCP method payloads, plus a `SchemaValidator` class and `CustomSchemaManager` for per-tool argument/output validation with schema caching and versioning. - npm: https://www.npmjs.com/package/@reaatech/mcp-gateway-validation - detail: https://reaatech.com/products/mcp-infrastructure/mcp-gateway/packages/mcp-gateway-validation - repo: https://github.com/reaatech/mcp-gateway ## @reaatech/mcp-schema-evolution **Category:** MCP Infrastructure · **Repo:** mcp-schema-evolution · **Status:** published v0.0.0 A function that compares two MCP `Tool[]` snapshots and returns a classified list of schema changes (breaking, non-breaking, or patch) with migration guidance, including heuristic-based field rename detection. - npm: https://www.npmjs.com/package/@reaatech/mcp-schema-evolution - detail: https://reaatech.com/products/mcp-infrastructure/mcp-schema-evolution/packages/mcp-schema-evolution - repo: https://github.com/reaatech/mcp-schema-evolution - tags: mcp, schema, evolution, json-schema, diff, backward-compatibility, model-context-protocol ## @reaatech/mcp-schema-evolution-ci **Category:** MCP Infrastructure · **Repo:** mcp-schema-evolution · **Status:** published v0.0.0 A CLI and programmatic API that validates MCP schema snapshots against a policy, failing CI on unacknowledged breaking changes and generating formatted reports for pull request comments. - npm: https://www.npmjs.com/package/@reaatech/mcp-schema-evolution-ci - detail: https://reaatech.com/products/mcp-infrastructure/mcp-schema-evolution/packages/mcp-schema-evolution-ci - repo: https://github.com/reaatech/mcp-schema-evolution - tags: mcp, schema, evolution, ci, json-schema, backward-compatibility, github-actions, model-context-protocol ## @reaatech/mcp-schema-evolution-cli **Category:** MCP Infrastructure · **Repo:** mcp-schema-evolution · **Status:** published v0.0.0 A CLI that compares two MCP tool snapshot JSON files, detects breaking and non-breaking schema changes, and outputs results as either human-readable text with migration suggestions or machine-readable JSON for CI pipelines. - npm: https://www.npmjs.com/package/@reaatech/mcp-schema-evolution-cli - detail: https://reaatech.com/products/mcp-infrastructure/mcp-schema-evolution/packages/mcp-schema-evolution-cli - repo: https://github.com/reaatech/mcp-schema-evolution - tags: mcp, schema, evolution, cli, json-schema, backward-compatibility, model-context-protocol ## @reaatech/mcp-server-auth **Category:** MCP Infrastructure · **Repo:** mcp-server-starter-ts · **Status:** published v1.1.0 Express middleware that validates incoming MCP server requests via API key or Bearer token using constant-time comparison, with an automatic dev-mode bypass when no key is configured. - npm: https://www.npmjs.com/package/@reaatech/mcp-server-auth - detail: https://reaatech.com/products/mcp-infrastructure/mcp-server-starter-ts/packages/mcp-server-auth - repo: https://github.com/reaatech/mcp-server-starter-ts ## @reaatech/mcp-server-core **Category:** MCP Infrastructure · **Repo:** mcp-server-starter-ts · **Status:** published v1.1.0 Provides shared Zod schemas, domain types (`ToolResponse`, `ContentBlock`, `RequestContext`), validated environment configuration, and content block factories for the `@reaatech/mcp-server-*` ecosystem. Exports TypeScript types and runtime validation helpers, with no runtime dependencies beyond Zod. - npm: https://www.npmjs.com/package/@reaatech/mcp-server-core - detail: https://reaatech.com/products/mcp-infrastructure/mcp-server-starter-ts/packages/mcp-server-core - repo: https://github.com/reaatech/mcp-server-starter-ts ## @reaatech/mcp-server-engine **Category:** MCP Infrastructure · **Repo:** mcp-server-starter-ts · **Status:** published v1.0.4 An Express 5-based MCP server framework that provides a composable middleware pipeline (auth, rate limiting, idempotency, sanitization), dual transport support (Streamable HTTP + SSE), automatic tool discovery and orchestration, health endpoints, OpenTelemetry tracing, and graceful shutdown. Exports `createApp()` (returns a configured Express app) and `startServer()` (listens on PORT with shutdown handlers). - npm: https://www.npmjs.com/package/@reaatech/mcp-server-engine - detail: https://reaatech.com/products/mcp-infrastructure/mcp-server-starter-ts/packages/mcp-server-engine - repo: https://github.com/reaatech/mcp-server-starter-ts ## @reaatech/mcp-server-observability **Category:** MCP Infrastructure · **Repo:** mcp-server-starter-ts · **Status:** published v1.2.0 Provides structured logging (Pino-based with PII redaction), OpenTelemetry tracing with OTLP export, and Prometheus-compatible metrics for MCP servers, exporting a logger, `initObservability()`, `withSpan()`, and metric recording functions. - npm: https://www.npmjs.com/package/@reaatech/mcp-server-observability - detail: https://reaatech.com/products/mcp-infrastructure/mcp-server-starter-ts/packages/mcp-server-observability - repo: https://github.com/reaatech/mcp-server-starter-ts ## @reaatech/mcp-server-tools **Category:** MCP Infrastructure · **Repo:** mcp-server-starter-ts · **Status:** published v1.1.0 A type-safe tool registry and discovery system for MCP servers, providing a `defineTool()` helper with Zod input schemas, an in-memory registry with `registerTool`/`getTools`/`getTool`/`clearTools`, filesystem auto-discovery of `.tool.ts` files, and built-in `echo` and `health-check` tools. - npm: https://www.npmjs.com/package/@reaatech/mcp-server-tools - detail: https://reaatech.com/products/mcp-infrastructure/mcp-server-starter-ts/packages/mcp-server-tools - repo: https://github.com/reaatech/mcp-server-starter-ts ## @reaatech/mcp-server-transport **Category:** MCP Infrastructure · **Repo:** mcp-server-starter-ts · **Status:** published v1.2.1 Mounts MCP transport handlers (Streamable HTTP and SSE) onto an Express or Fastify application, managing session lifecycle, automatic cleanup, and transport-level metrics. Exports `mountStreamableHTTP`, `mountSSE`, and Fastify plugin functions that accept a server factory and optional path configuration. - npm: https://www.npmjs.com/package/@reaatech/mcp-server-transport - detail: https://reaatech.com/products/mcp-infrastructure/mcp-server-starter-ts/packages/mcp-server-transport - repo: https://github.com/reaatech/mcp-server-starter-ts ## @reaatech/multi-tenant-mcp-artifact-store **Category:** MCP Infrastructure · **Repo:** multi-tenant-mcp · **Status:** published v0.1.0 Tenant-isolated artifact and file storage with automatic namespace prefixing, path traversal protection, and configurable per-tenant quotas. Provides `FileSystemArtifactStore` and `S3ArtifactStore` classes implementing a common `ArtifactStore` interface (`put`, `get`, `list`, `delete`, `exists`), plus an `ArtifactLifecycleManager` for TTL-based cleanup; the S3 backend requires `@aws-sdk/client-s3` as a peer dependency. - npm: https://www.npmjs.com/package/@reaatech/multi-tenant-mcp-artifact-store - detail: https://reaatech.com/products/mcp-infrastructure/multi-tenant-mcp/packages/multi-tenant-mcp-artifact-store - repo: https://github.com/reaatech/multi-tenant-mcp ## @reaatech/multi-tenant-mcp-config-isolation **Category:** MCP Infrastructure · **Repo:** multi-tenant-mcp · **Status:** published v0.1.0 A Zod-validated per-tenant configuration manager with base-config inheritance, pluggable storage, and versioned migration support. Exports `TenantConfigManager`, `ZodConfigValidator`, `InMemoryConfigStore`, and `ConfigMigrationRunner` classes, plus `TenantConfigStore` and `ConfigValidator` interfaces for custom backends. - npm: https://www.npmjs.com/package/@reaatech/multi-tenant-mcp-config-isolation - detail: https://reaatech.com/products/mcp-infrastructure/multi-tenant-mcp/packages/multi-tenant-mcp-config-isolation - repo: https://github.com/reaatech/multi-tenant-mcp ## @reaatech/multi-tenant-mcp-cost-accounting **Category:** MCP Infrastructure · **Repo:** multi-tenant-mcp · **Status:** published v0.1.0 Provides interfaces and classes for per-tenant cost tracking in MCP servers, supporting per-call, per-token, and tiered discount pricing models with non-blocking usage event emission. - npm: https://www.npmjs.com/package/@reaatech/multi-tenant-mcp-cost-accounting - detail: https://reaatech.com/products/mcp-infrastructure/multi-tenant-mcp/packages/multi-tenant-mcp-cost-accounting - repo: https://github.com/reaatech/multi-tenant-mcp ## @reaatech/multi-tenant-mcp-middleware **Category:** MCP Infrastructure · **Repo:** multi-tenant-mcp · **Status:** published v0.1.0 A function that wraps MCP server request handlers with a configurable pipeline for tenant resolution, rate limiting, tool/resource/prompt visibility filtering, cost accounting, logging, and metrics. - npm: https://www.npmjs.com/package/@reaatech/multi-tenant-mcp-middleware - detail: https://reaatech.com/products/mcp-infrastructure/multi-tenant-mcp/packages/multi-tenant-mcp-middleware - repo: https://github.com/reaatech/multi-tenant-mcp ## @reaatech/multi-tenant-mcp-observability **Category:** MCP Infrastructure · **Repo:** multi-tenant-mcp · **Status:** published v0.1.0 Provides structured console logging and LRU-bounded per-tenant metrics for multi-tenant MCP servers, exporting `ConsoleTenantLogger` and `MetricsCollector` classes that automatically attach the current tenant ID from a `TenantContextStore`. - npm: https://www.npmjs.com/package/@reaatech/multi-tenant-mcp-observability - detail: https://reaatech.com/products/mcp-infrastructure/multi-tenant-mcp/packages/multi-tenant-mcp-observability - repo: https://github.com/reaatech/multi-tenant-mcp ## @reaatech/multi-tenant-mcp-rate-limiter **Category:** MCP Infrastructure · **Repo:** multi-tenant-mcp · **Status:** published v0.1.0 A per-tenant rate limiter for MCP servers that enforces fixed-window request and token quotas, exposing a `DefaultRateLimiter` class backed by either an in-memory `MemoryRateLimitStore` (single-process) or a `RedisRateLimitStore` (distributed). - npm: https://www.npmjs.com/package/@reaatech/multi-tenant-mcp-rate-limiter - detail: https://reaatech.com/products/mcp-infrastructure/multi-tenant-mcp/packages/multi-tenant-mcp-rate-limiter - repo: https://github.com/reaatech/multi-tenant-mcp ## @reaatech/multi-tenant-mcp-tenant-resolver **Category:** MCP Infrastructure · **Repo:** multi-tenant-mcp · **Status:** published v0.1.0 Resolve tenant identity from incoming MCP requests via headers, JWTs, or API keys, and propagate it through `AsyncLocalStorage`. Exports resolver classes (`HeaderTenantResolver`, `JWTTenantResolver`, `APIKeyTenantResolver`) and a `TenantContextStore` for context propagation; JWT support requires the optional `jsonwebtoken` peer. - npm: https://www.npmjs.com/package/@reaatech/multi-tenant-mcp-tenant-resolver - detail: https://reaatech.com/products/mcp-infrastructure/multi-tenant-mcp/packages/multi-tenant-mcp-tenant-resolver - repo: https://github.com/reaatech/multi-tenant-mcp ## @reaatech/multi-tenant-mcp-tool-visibility **Category:** MCP Infrastructure · **Repo:** multi-tenant-mcp · **Status:** published v0.1.0 A class (`VisibilityEngineImpl`) and interface (`VisibilityEngine`) that control which MCP tools, resources, and prompts each tenant can see, supporting allow-list, deny-list, and runtime-evaluator policies. - npm: https://www.npmjs.com/package/@reaatech/multi-tenant-mcp-tool-visibility - detail: https://reaatech.com/products/mcp-infrastructure/multi-tenant-mcp/packages/multi-tenant-mcp-tool-visibility - repo: https://github.com/reaatech/multi-tenant-mcp ## @reaatech/multi-tenant-mcp-types **Category:** MCP Infrastructure · **Repo:** multi-tenant-mcp · **Status:** published v0.1.0 Shared TypeScript types, error classes, and data structures for the multi-tenant MCP ecosystem, including `TenantContext`, `MiddlewareError`, `MiddlewareErrorCode`, and `BoundedMap`. - npm: https://www.npmjs.com/package/@reaatech/multi-tenant-mcp-types - detail: https://reaatech.com/products/mcp-infrastructure/multi-tenant-mcp/packages/multi-tenant-mcp-types - repo: https://github.com/reaatech/multi-tenant-mcp ## @reaatech/webhook-relay-core **Category:** MCP Infrastructure · **Repo:** webhook-relay-mcp · **Status:** published v0.2.0 Shared types, configuration loading, AES-256-GCM encryption helpers, a filter DSL evaluator, Prometheus metric registry, and a shared pino logger for the webhook-relay-mcp project. Provides Zod-validated environment config, event/source type definitions, and filter operators (`$eq`, `$gt`, `$in`, `$regex`, `$and`, `$or`, `$not`) as exported modules. - npm: https://www.npmjs.com/package/@reaatech/webhook-relay-core - detail: https://reaatech.com/products/mcp-infrastructure/webhook-relay-mcp/packages/webhook-relay-core - repo: https://github.com/reaatech/webhook-relay-mcp ## @reaatech/webhook-relay-mcp **Category:** MCP Infrastructure · **Repo:** webhook-relay-mcp · **Status:** published v0.2.0 A CLI binary (`webhook-relay-mcp`) that runs an MCP server bridging third-party webhooks (Stripe, GitHub, Replicate, Twilio, SendGrid, Slack, Vercel, and generic sources) into agent workflows, bundling an HTTP ingestion server, MCP transport (stdio or HTTP/SSE), and an admin dashboard. Requires an `ENCRYPTION_KEY` environment variable and transitively depends on `better-sqlite3`. - npm: https://www.npmjs.com/package/@reaatech/webhook-relay-mcp - detail: https://reaatech.com/products/mcp-infrastructure/webhook-relay-mcp/packages/webhook-relay-mcp - repo: https://github.com/reaatech/webhook-relay-mcp ## @reaatech/webhook-relay-storage **Category:** MCP Infrastructure · **Repo:** webhook-relay-mcp · **Status:** published v0.2.0 SQLite storage layer for webhook-relay-mcp, providing schema migrations and repository classes (Events, Subscriptions, Sources, Audit) plus services (Cleanup, Delivery with retry and DLQ, Audit, SourceHealth, PollWaiter) backed by better-sqlite3 with WAL mode and foreign keys. - npm: https://www.npmjs.com/package/@reaatech/webhook-relay-storage - detail: https://reaatech.com/products/mcp-infrastructure/webhook-relay-mcp/packages/webhook-relay-storage - repo: https://github.com/reaatech/webhook-relay-mcp ## @reaatech/webhook-relay-tools **Category:** MCP Infrastructure · **Repo:** webhook-relay-mcp · **Status:** published v0.2.0 A library that exposes an MCP server and 15 webhook management tools (subscribe, unsubscribe, list, poll, history, register, stats, replay, update-source, delete-source, rotate-secret, list-sources, audit-log, source-health, event-types) via the `startMCPServer()` function, built on `@modelcontextprotocol/sdk`. - npm: https://www.npmjs.com/package/@reaatech/webhook-relay-tools - detail: https://reaatech.com/products/mcp-infrastructure/webhook-relay-mcp/packages/webhook-relay-tools - repo: https://github.com/reaatech/webhook-relay-mcp ## @reaatech/webhook-relay-webhooks **Category:** MCP Infrastructure · **Repo:** webhook-relay-mcp · **Status:** published v0.2.0 Provides webhook ingestion logic including signature validators (HMAC-SHA256/SHA1 with constant-time comparison), source handlers for Stripe, GitHub, Replicate, Twilio, SendGrid, Slack, Vercel, and a generic handler, plus payload normalization into a unified event schema and ingress-level deduplication by `webhookId`. It exports handler functions and validators intended as internal building blocks for the `@reaatech/webhook-relay-mcp` server. - npm: https://www.npmjs.com/package/@reaatech/webhook-relay-webhooks - detail: https://reaatech.com/products/mcp-infrastructure/webhook-relay-mcp/packages/webhook-relay-webhooks - repo: https://github.com/reaatech/webhook-relay-mcp # Reliability & Ops > 44 packages — Circuit breakers, idempotency, output repair, secret rotation, session continuity. ## @reaatech/agent-runbook **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 Shared domain types, Zod schemas, utility functions, and error classes for the Agent Runbook Generator ecosystem. Exports TypeScript interfaces (e.g., `Runbook`, `ServiceDefinition`, `FailureMode`), Zod schemas for runtime validation, helper functions (file I/O, ID generation, markdown), and typed error classes—all with zero runtime dependencies beyond `zod`. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-agent **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 An AI agent class (`AnalysisAgent`) and factory function (`createAnalysisAgent`) that wraps Anthropic Claude, OpenAI, and Google Gemini LLMs with pre-built prompt templates for automated code analysis, failure mode identification, and runbook section generation. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-agent - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-agent - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-alerts **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 Extracts existing alert definitions from Prometheus, Datadog, and CloudWatch configs and generates new SLO-based, resource, and application alerts, providing functions like `extractAlerts`, `generateAlerts`, and `formatAlertsForPlatform`. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-alerts - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-alerts - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-analyzer **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 Scans a service repository to detect its language, framework, deployment platform, configuration files, entry points, API endpoints, external service connections, and package dependencies, returning structured analysis objects from functions like `scanRepository`, `mapDependencies`, `parseConfigs`, and `analyzeCode`. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-analyzer - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-analyzer - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-cli **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 A CLI and programmatic entry point that generates operator runbooks from service repositories using AI analysis, providing five commands (`analyze`, `generate`, `validate`, `export`, `serve`) and re-exporting all public APIs from the `@reaatech/agent-runbook-*` ecosystem. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-cli - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-cli - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-dashboards **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 Generates Grafana and CloudWatch dashboard configurations by scanning a codebase to identify relevant service metrics and producing complete dashboard panels with queries, thresholds, and legends. Exports functions like `identifyMetrics`, `generateDashboard`, and platform-specific formatters. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-dashboards - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-dashboards - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-e2e **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** pending npm - npm: pending — package not yet published as @reaatech/agent-runbook-e2e - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-e2e - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-failure-modes **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 Identifies potential failure points in a codebase by analyzing code patterns, categorizes them into 10 types (e.g., dependency, security, database) with severity scores, and generates actionable mitigation strategies including circuit breaker and retry configurations. Exports functions like `identifyFailureModes`, `generateMitigations`, and `getAllFailureModes`. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-failure-modes - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-failure-modes - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-health-checks **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 Identifies existing health check endpoints in a codebase and generates liveness, readiness, and startup probe definitions for Kubernetes and load balancers. Exports functions like `identifyHealthChecks`, `generateHealthChecks`, `generateKubernetesProbeYaml`, and `generateLoadBalancerConfig`. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-health-checks - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-health-checks - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-incident **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 Generates SEV1–SEV4 incident response workflows, escalation policies, and communication templates for the Agent Runbook Generator. Exports functions like `generateIncidentWorkflows`, `generateEscalationPolicy`, and `getTemplatesByCategory` that take an analysis context and configuration and return structured workflow and template objects. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-incident - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-incident - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-mcp **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 An MCP server that exposes 16 tools for analyzing repository structure, generating operator runbooks, and validating runbook completeness, consumable by AI coding agents via stdio transport. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-mcp - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-mcp - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-observability **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 Provides structured logging via Pino, distributed tracing via OpenTelemetry, and Prometheus-compatible metrics for tracking runbook generation, agent costs, and quality. Exports a set of initialization functions and recording helpers (e.g., `initLogger`, `startGenerationSpan`, `recordGeneration`). - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-observability - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-observability - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-rollback **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 Exports functions (`analyzeDeployment`, `generateRollbackProcedures`, `generateVerificationSteps`) that analyze a deployment configuration and produce structured rollback procedures—including pre-checks, platform-specific commands, and verification steps—for Kubernetes, ECS, Cloud Run, and other platforms. Depends on `@reaatech/agent-runbook` for core types. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-rollback - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-rollback - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-runbook **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 Assembles analysis results from the Agent Runbook Generator pipeline into a structured operator runbook with auto-generated table of contents, cross-references, and validation, exporting to Markdown, HTML, or PDF. Exports functions like `generateRunbookArtifacts`, `exportRunbook`, and `validateCompleteness`. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-runbook - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-runbook - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/agent-runbook-service-map **Category:** Reliability & Ops · **Repo:** agent-runbook-generator · **Status:** published v0.1.0 Exports functions (`analyzeDependencies`, `generateServiceMap`, `exportGraph`) that analyze inter-service dependencies in a codebase, build directed dependency graphs with critical path analysis, and export them as Mermaid, DOT, JSON, or YAML. - npm: https://www.npmjs.com/package/@reaatech/agent-runbook-service-map - detail: https://reaatech.com/products/reliability-ops/agent-runbook-generator/packages/agent-runbook-service-map - repo: https://github.com/reaatech/agent-runbook-generator ## @reaatech/circuit-breaker-agents **Category:** Reliability & Ops · **Repo:** circuit-breaker-agents · **Status:** published v0.1.1 A meta-package that re-exports all public APIs from `@reaatech/circuit-breaker-core` and `@reaatech/circuit-breaker-persistence` as a single dependency, providing classes (`CircuitBreaker`, `StateMachine`), persistence adapters (`InMemoryAdapter`, `FirestoreAdapter`, `DynamoDBAdapter`, `RedisAdapter`), leader election, strategies, metrics collectors, error classes, and TypeScript types. - npm: https://www.npmjs.com/package/@reaatech/circuit-breaker-agents - detail: https://reaatech.com/products/reliability-ops/circuit-breaker-agents/packages/circuit-breaker-agents - repo: https://github.com/reaatech/circuit-breaker-agents ## @reaatech/circuit-breaker-core **Category:** Reliability & Ops · **Repo:** circuit-breaker-agents · **Status:** published v0.1.1 A circuit breaker state machine for agent-to-tool and agent-to-agent communication, providing a `CircuitBreaker` class with lazy auto-transition state evaluation, configurable trip strategies (error threshold, confidence threshold, cost threshold), recovery strategies (gradual exponential ramp-up or single all-or-nothing), and pluggable metrics collection — depends only on `zod` at runtime. - npm: https://www.npmjs.com/package/@reaatech/circuit-breaker-core - detail: https://reaatech.com/products/reliability-ops/circuit-breaker-agents/packages/circuit-breaker-core - repo: https://github.com/reaatech/circuit-breaker-agents ## @reaatech/circuit-breaker-example-basic **Category:** Reliability & Ops · **Repo:** circuit-breaker-agents · **Status:** pending npm Description pending. - npm: pending — package not yet published as @reaatech/circuit-breaker-example-basic - detail: https://reaatech.com/products/reliability-ops/circuit-breaker-agents/packages/circuit-breaker-example-basic - repo: https://github.com/reaatech/circuit-breaker-agents ## @reaatech/circuit-breaker-example-dynamodb **Category:** Reliability & Ops · **Repo:** circuit-breaker-agents · **Status:** pending npm Description pending. - npm: pending — package not yet published as @reaatech/circuit-breaker-example-dynamodb - detail: https://reaatech.com/products/reliability-ops/circuit-breaker-agents/packages/circuit-breaker-example-dynamodb - repo: https://github.com/reaatech/circuit-breaker-agents ## @reaatech/circuit-breaker-example-firestore **Category:** Reliability & Ops · **Repo:** circuit-breaker-agents · **Status:** pending npm Description pending. - npm: pending — package not yet published as @reaatech/circuit-breaker-example-firestore - detail: https://reaatech.com/products/reliability-ops/circuit-breaker-agents/packages/circuit-breaker-example-firestore - repo: https://github.com/reaatech/circuit-breaker-agents ## @reaatech/circuit-breaker-example-redis **Category:** Reliability & Ops · **Repo:** circuit-breaker-agents · **Status:** pending npm Description pending. - npm: pending — package not yet published as @reaatech/circuit-breaker-example-redis - detail: https://reaatech.com/products/reliability-ops/circuit-breaker-agents/packages/circuit-breaker-example-redis - repo: https://github.com/reaatech/circuit-breaker-agents ## @reaatech/circuit-breaker-persistence **Category:** Reliability & Ops · **Repo:** circuit-breaker-agents · **Status:** published v0.1.1 Persistence adapters for circuit breaker state that survive restarts and share state across instances. Exports a `PersistenceAdapter` interface with four implementations: `InMemoryAdapter` (zero dependencies), `FirestoreAdapter` (peer: `@google-cloud/firestore`), `DynamoDBAdapter` (peer: `@aws-sdk/client-dynamodb`), and `RedisAdapter` (peer: `ioredis`), each providing `connect`, `disconnect`, `saveState`, `loadState`, `deleteState`, `saveBatch`, `loadAll`, `tryAcquireLeadership`, `releaseLeadership`, and `healthCheck` methods. - npm: https://www.npmjs.com/package/@reaatech/circuit-breaker-persistence - detail: https://reaatech.com/products/reliability-ops/circuit-breaker-agents/packages/circuit-breaker-persistence - repo: https://github.com/reaatech/circuit-breaker-agents ## @reaatech/idempotency-middleware **Category:** Reliability & Ops · **Repo:** idempotency-middleware · **Status:** published v1.0.0 A framework-agnostic TypeScript middleware that makes POST, PUT, and PATCH requests idempotent by caching responses keyed to an `Idempotency-Key` header, with pluggable storage adapters (in-memory, Redis, DynamoDB, Firestore) and distributed locking to prevent concurrent handler execution for the same key. Exports an `IdempotencyMiddleware` class with an `execute` method that wraps any async handler. - npm: https://www.npmjs.com/package/@reaatech/idempotency-middleware - detail: https://reaatech.com/products/reliability-ops/idempotency-middleware/packages/idempotency-middleware - repo: https://github.com/reaatech/idempotency-middleware - tags: idempotency, middleware, cache, typescript ## @reaatech/idempotency-middleware-adapter-dynamodb **Category:** Reliability & Ops · **Repo:** idempotency-middleware · **Status:** published v1.0.1 A DynamoDB storage adapter for `@reaatech/idempotency-middleware` that implements the `StorageAdapter` interface using conditional writes for distributed locking and TTL-compatible `expiresAt` attributes. It pairs with `@aws-sdk/client-dynamodb` and `@aws-sdk/util-dynamodb` at runtime. - npm: https://www.npmjs.com/package/@reaatech/idempotency-middleware-adapter-dynamodb - detail: https://reaatech.com/products/reliability-ops/idempotency-middleware/packages/idempotency-middleware-adapter-dynamodb - repo: https://github.com/reaatech/idempotency-middleware ## @reaatech/idempotency-middleware-adapter-firestore **Category:** Reliability & Ops · **Repo:** idempotency-middleware · **Status:** published v1.1.0 A Firestore storage adapter for `@reaatech/idempotency-middleware` that provides transaction-gated distributed locking and TTL-compatible expiry via `expiresAt` Date fields. Exports a `FirestoreAdapter` class implementing the `StorageAdapter` interface, requiring a `@google-cloud/firestore` `Firestore` instance and an optional collection name. - npm: https://www.npmjs.com/package/@reaatech/idempotency-middleware-adapter-firestore - detail: https://reaatech.com/products/reliability-ops/idempotency-middleware/packages/idempotency-middleware-adapter-firestore - repo: https://github.com/reaatech/idempotency-middleware ## @reaatech/idempotency-middleware-adapter-redis **Category:** Reliability & Ops · **Repo:** idempotency-middleware · **Status:** published v1.0.0 Redis storage adapter for `@reaatech/idempotency-middleware` that implements the `StorageAdapter` interface using ioredis, providing distributed idempotency caching with token-guarded locking via `SET NX` and Lua-based lock release. - npm: https://www.npmjs.com/package/@reaatech/idempotency-middleware-adapter-redis - detail: https://reaatech.com/products/reliability-ops/idempotency-middleware/packages/idempotency-middleware-adapter-redis - repo: https://github.com/reaatech/idempotency-middleware ## @reaatech/idempotency-middleware-express **Category:** Reliability & Ops · **Repo:** idempotency-middleware · **Status:** published v1.0.0 Express middleware that caches responses keyed by the `Idempotency-Key` header, preventing duplicate processing of retried requests. It monkey-patches `res.json()` and `res.send()` to capture response bodies, and requires a storage adapter from `@reaatech/idempotency-middleware` (e.g., `MemoryAdapter`). - npm: https://www.npmjs.com/package/@reaatech/idempotency-middleware-express - detail: https://reaatech.com/products/reliability-ops/idempotency-middleware/packages/idempotency-middleware-express - repo: https://github.com/reaatech/idempotency-middleware ## @reaatech/idempotency-middleware-koa **Category:** Reliability & Ops · **Repo:** idempotency-middleware · **Status:** published v1.0.0 Koa middleware that caches responses keyed by the `Idempotency-Key` header, preventing duplicate processing of the same request. It provides an `idempotentKoa(storage, config?)` function that wraps route handlers, automatically capturing `ctx.body` and `ctx.status` after `await next()` for replay on subsequent identical requests. Requires `koa` and a body parser middleware like `koa-bodyparser`. - npm: https://www.npmjs.com/package/@reaatech/idempotency-middleware-koa - detail: https://reaatech.com/products/reliability-ops/idempotency-middleware/packages/idempotency-middleware-koa - repo: https://github.com/reaatech/idempotency-middleware ## @reaatech/secret-rotation-core **Category:** Reliability & Ops · **Repo:** secret-rotation-kit · **Status:** published v0.1.0 A zero-downtime secret rotation engine that orchestrates the full lifecycle (generate → propagate → verify → activate → revoke) with overlapping key windows, dual verification strategies, and automatic rollback. Exports a `RotationManager` class that accepts a pluggable provider adapter (e.g., AWS, GCP, Vault) and optional key store, verifier, event emitter, and rate limiter. - npm: https://www.npmjs.com/package/@reaatech/secret-rotation-core - detail: https://reaatech.com/products/reliability-ops/secret-rotation-kit/packages/secret-rotation-core - repo: https://github.com/reaatech/secret-rotation-kit ## @reaatech/secret-rotation-observability **Category:** Reliability & Ops · **Repo:** secret-rotation-kit · **Status:** published v0.1.0 A structured JSON logger and Prometheus-format metrics registry with zero runtime dependencies, providing `LoggerService` and `MetricsService` classes that implement the `Logger` interface from `@reaatech/secret-rotation-types`. - npm: https://www.npmjs.com/package/@reaatech/secret-rotation-observability - detail: https://reaatech.com/products/reliability-ops/secret-rotation-kit/packages/secret-rotation-observability - repo: https://github.com/reaatech/secret-rotation-kit ## @reaatech/secret-rotation-provider-aws **Category:** Reliability & Ops · **Repo:** secret-rotation-kit · **Status:** published v0.1.0 An AWS Secrets Manager adapter for the Secret Rotation Kit, implementing the `SecretProvider` interface with CRUD operations, version stage management (`AWSCURRENT`, `AWSPENDING`, `AWSPREVIOUS`), and rotation session support. Requires `@aws-sdk/client-secrets-manager` as a peer dependency. - npm: https://www.npmjs.com/package/@reaatech/secret-rotation-provider-aws - detail: https://reaatech.com/products/reliability-ops/secret-rotation-kit/packages/secret-rotation-provider-aws - repo: https://github.com/reaatech/secret-rotation-kit ## @reaatech/secret-rotation-provider-gcp **Category:** Reliability & Ops · **Repo:** secret-rotation-kit · **Status:** published v1.0.0 GCP Secret Manager adapter for the Secret Rotation Kit, implementing the `SecretProvider` interface with CRUD, versioning, rotation sessions, and health checks via the `@google-cloud/secret-manager` SDK. - npm: https://www.npmjs.com/package/@reaatech/secret-rotation-provider-gcp - detail: https://reaatech.com/products/reliability-ops/secret-rotation-kit/packages/secret-rotation-provider-gcp - repo: https://github.com/reaatech/secret-rotation-kit ## @reaatech/secret-rotation-provider-vault **Category:** Reliability & Ops · **Repo:** secret-rotation-kit · **Status:** published v0.1.0 A HashiCorp Vault KV v2 adapter for the Secret Rotation Kit, implementing the `SecretProvider` interface with CRUD, versioning, rotation sessions, and health checks. It provides a `VaultProvider` class that pairs with `@reaatech/secret-rotation-core` and lazily loads the `node-vault` client at runtime. - npm: https://www.npmjs.com/package/@reaatech/secret-rotation-provider-vault - detail: https://reaatech.com/products/reliability-ops/secret-rotation-kit/packages/secret-rotation-provider-vault - repo: https://github.com/reaatech/secret-rotation-kit ## @reaatech/secret-rotation-provider-vercel **Category:** Reliability & Ops · **Repo:** secret-rotation-kit · **Status:** published v0.1.0 A Vercel-specific `SecretProvider` implementation for the Secret Rotation Kit that manages environment variables via the Vercel REST API using only the global `fetch`. It provides a class (`VercelProvider`) that handles CRUD operations, rotation sessions, and health checks against Vercel projects, with support for multiple deployment targets and configurable environment variable types. - npm: https://www.npmjs.com/package/@reaatech/secret-rotation-provider-vercel - detail: https://reaatech.com/products/reliability-ops/secret-rotation-kit/packages/secret-rotation-provider-vercel - repo: https://github.com/reaatech/secret-rotation-kit ## @reaatech/secret-rotation-sidecar **Category:** Reliability & Ops · **Repo:** secret-rotation-kit · **Status:** published v1.0.0 HTTP sidecar server that exposes secret rotation operations, health checks, Prometheus metrics, and SSE event streaming over a REST API, built on Node.js's built-in `http` module with zero framework dependencies. Ships as both a programmatic class (`SidecarServer`) and a standalone CLI binary configured via environment variables. - npm: https://www.npmjs.com/package/@reaatech/secret-rotation-sidecar - detail: https://reaatech.com/products/reliability-ops/secret-rotation-kit/packages/secret-rotation-sidecar - repo: https://github.com/reaatech/secret-rotation-kit ## @reaatech/secret-rotation-types **Category:** Reliability & Ops · **Repo:** secret-rotation-kit · **Status:** published v0.1.0 Type definitions, abstract interfaces, and error classes for the Secret Rotation Kit ecosystem, providing shared types like `SecretKey`, `RotationState`, `SecretProvider`, and `RotationConfig` as zero-dependency TypeScript exports. - npm: https://www.npmjs.com/package/@reaatech/secret-rotation-types - detail: https://reaatech.com/products/reliability-ops/secret-rotation-kit/packages/secret-rotation-types - repo: https://github.com/reaatech/secret-rotation-kit ## @reaatech/session-continuity **Category:** Reliability & Ops · **Repo:** session-continuity-kit · **Status:** published v0.1.0 A typed session lifecycle manager for multi-turn AI conversations, providing `SessionManager` with token budget enforcement, configurable context compression (sliding window, summarization, or hybrid), optimistic concurrency, and a storage-agnostic `IStorageAdapter` interface. - npm: https://www.npmjs.com/package/@reaatech/session-continuity - detail: https://reaatech.com/products/reliability-ops/session-continuity-kit/packages/session-continuity - repo: https://github.com/reaatech/session-continuity-kit - tags: ai, agent, llm, session, conversation, token-budget, compression ## @reaatech/session-continuity-storage-dynamodb **Category:** Reliability & Ops · **Repo:** session-continuity-kit · **Status:** published v0.1.0 A DynamoDB storage adapter implementing `IStorageAdapter` from `@reaatech/session-continuity`, providing session and message persistence using a single-table design with composite keys and two global secondary indexes. It pairs with `@aws-sdk/client-dynamodb` and `@aws-sdk/lib-dynamodb` at runtime. - npm: https://www.npmjs.com/package/@reaatech/session-continuity-storage-dynamodb - detail: https://reaatech.com/products/reliability-ops/session-continuity-kit/packages/session-continuity-storage-dynamodb - repo: https://github.com/reaatech/session-continuity-kit - tags: session-continuity-kit, storage-adapter, dynamodb, aws ## @reaatech/session-continuity-storage-firestore **Category:** Reliability & Ops · **Repo:** session-continuity-kit · **Status:** published v0.1.0 A Firestore storage adapter implementing `IStorageAdapter` from `@reaatech/session-continuity`, providing session and message persistence in Firestore collections with TTL support, batch operations, and optimistic concurrency via transactions. - npm: https://www.npmjs.com/package/@reaatech/session-continuity-storage-firestore - detail: https://reaatech.com/products/reliability-ops/session-continuity-kit/packages/session-continuity-storage-firestore - repo: https://github.com/reaatech/session-continuity-kit - tags: session-continuity-kit, storage-adapter, firestore, google-cloud ## @reaatech/session-continuity-storage-memory **Category:** Reliability & Ops · **Repo:** session-continuity-kit · **Status:** published v0.1.0 An in-memory storage adapter implementing `IStorageAdapter` from `@reaatech/session-continuity`, using `Map`-based storage with optional simulated TTL expiration for development, testing, and single-process prototypes. - npm: https://www.npmjs.com/package/@reaatech/session-continuity-storage-memory - detail: https://reaatech.com/products/reliability-ops/session-continuity-kit/packages/session-continuity-storage-memory - repo: https://github.com/reaatech/session-continuity-kit - tags: session-continuity-kit, storage-adapter, in-memory, testing ## @reaatech/session-continuity-storage-redis **Category:** Reliability & Ops · **Repo:** session-continuity-kit · **Status:** published v0.1.0 A Redis storage adapter implementing `IStorageAdapter` from `@reaatech/session-continuity`, providing session and message persistence using Redis hashes, sorted sets, and native TTL with optimistic concurrency via `WATCH`/`MULTI`/`EXEC` transactions. Requires a `redis` v4+ client instance and the `@reaatech/session-continuity` package. - npm: https://www.npmjs.com/package/@reaatech/session-continuity-storage-redis - detail: https://reaatech.com/products/reliability-ops/session-continuity-kit/packages/session-continuity-storage-redis - repo: https://github.com/reaatech/session-continuity-kit - tags: session-continuity-kit, storage-adapter, redis ## @reaatech/session-continuity-tokenizers **Category:** Reliability & Ops · **Repo:** session-continuity-kit · **Status:** published v0.1.0 A set of token counter implementations (exact WASM-based tiktoken for OpenAI, exact Anthropic, and a fast heuristic estimator) that implement the `TokenCounter` interface from `@reaatech/session-continuity`, plus a factory that auto-selects the right tokenizer by model name. - npm: https://www.npmjs.com/package/@reaatech/session-continuity-tokenizers - detail: https://reaatech.com/products/reliability-ops/session-continuity-kit/packages/session-continuity-tokenizers - repo: https://github.com/reaatech/session-continuity-kit - tags: session-continuity-kit, tokenizer, tiktoken, anthropic, openai, llm ## @reaatech/structured-repair-core **Category:** Reliability & Ops · **Repo:** structured-output-repair · **Status:** published v1.1.0 A Zod schema–driven repair engine that applies six graduated strategies (prose extraction, truncation repair, type coercion, fuzzy key matching, extra field removal, and input analysis) to malformed LLM outputs, returning schema-conforming data or detailed failure metadata. Exports `repair`, `repairOutput`, `isValid`, and `analyzeInput` functions, and requires `zod` as a peer dependency. - npm: https://www.npmjs.com/package/@reaatech/structured-repair-core - detail: https://reaatech.com/products/reliability-ops/structured-output-repair/packages/structured-repair-core - repo: https://github.com/reaatech/structured-output-repair ## @reaatech/structured-repair-mcp **Category:** Reliability & Ops · **Repo:** structured-output-repair · **Status:** published v1.0.0 An MCP server that exposes `structured.repair` and `structured.analyze` as tools, letting MCP-compatible clients (Claude Desktop, Cursor) repair malformed LLM structured outputs against a JSON Schema. - npm: https://www.npmjs.com/package/@reaatech/structured-repair-mcp - detail: https://reaatech.com/products/reliability-ops/structured-output-repair/packages/structured-repair-mcp - repo: https://github.com/reaatech/structured-output-repair # Domain Pipelines > 45 packages — Hybrid RAG, voice agent kit, media pipelines, agent memory. ## @reaatech/agent-memory **Category:** Domain Pipelines · **Repo:** agent-memory · **Status:** published v0.1.0 A class that provides a long-term memory layer for AI agents, combining LLM-powered extraction, semantic search, configurable storage (in-memory or PostgreSQL pgvector), and lifecycle management (decay, forgetting, contradiction resolution) into a single facade. - npm: https://www.npmjs.com/package/@reaatech/agent-memory - detail: https://reaatech.com/products/domain-pipelines/agent-memory/packages/agent-memory - repo: https://github.com/reaatech/agent-memory ## @reaatech/agent-memory-core **Category:** Domain Pipelines · **Repo:** agent-memory · **Status:** published v0.1.0 Canonical TypeScript types, enums, and utilities for the agent-memory ecosystem, providing the `Memory` data structure, lifecycle states, importance levels, contradiction strategies, and shared helpers like `cosineSimilarity` and `withRetry`. Exports interfaces, enums, and functions with zero runtime dependencies and dual ESM/CJS output. - npm: https://www.npmjs.com/package/@reaatech/agent-memory-core - detail: https://reaatech.com/products/domain-pipelines/agent-memory/packages/agent-memory-core - repo: https://github.com/reaatech/agent-memory ## @reaatech/agent-memory-embedding **Category:** Domain Pipelines · **Repo:** agent-memory · **Status:** published v0.1.0 An embedding provider abstraction that exposes a unified `EmbeddingProvider` interface with `embed()` and `embedBatch()` methods, shipping adapters for OpenAI, Cohere, and HuggingFace, plus an `InMemoryEmbeddingCache` with LRU eviction and TTL that wraps any provider via `CachedEmbeddingProvider`. - npm: https://www.npmjs.com/package/@reaatech/agent-memory-embedding - detail: https://reaatech.com/products/domain-pipelines/agent-memory/packages/agent-memory-embedding - repo: https://github.com/reaatech/agent-memory ## @reaatech/agent-memory-events **Category:** Domain Pipelines · **Repo:** agent-memory · **Status:** published v0.1.0 An event bus and typed event types for agent-memory lifecycle hooks, providing `InMemoryEventBus` (a class with `on`, `off`, `once`, and `emit` methods) and nine event type constants (`memory:stored`, `memory:retrieved`, etc.) for publishing and subscribing to memory creation, retrieval, contradiction, decay, and forgetting events. - npm: https://www.npmjs.com/package/@reaatech/agent-memory-events - detail: https://reaatech.com/products/domain-pipelines/agent-memory/packages/agent-memory-events - repo: https://github.com/reaatech/agent-memory ## @reaatech/agent-memory-extraction **Category:** Domain Pipelines · **Repo:** agent-memory · **Status:** published v0.1.0 An LLM-powered memory extraction engine that analyzes conversation turns to identify and classify memorable facts, preferences, decisions, and corrections, returning structured candidates with importance scores, confidence levels, and embeddings for semantic search. It provides a `MemoryExtractor` class that requires an `LLMProvider` and an `EmbeddingProvider` at runtime. - npm: https://www.npmjs.com/package/@reaatech/agent-memory-extraction - detail: https://reaatech.com/products/domain-pipelines/agent-memory/packages/agent-memory-extraction - repo: https://github.com/reaatech/agent-memory ## @reaatech/agent-memory-llm **Category:** Domain Pipelines · **Repo:** agent-memory · **Status:** published v0.1.0 An `LLMProvider` interface and `OpenAILLMProvider` class that expose `complete()` for freeform text generation and `completeStructured()` for JSON-schema-constrained structured output, designed for memory extraction and classification in agent systems. - npm: https://www.npmjs.com/package/@reaatech/agent-memory-llm - detail: https://reaatech.com/products/domain-pipelines/agent-memory/packages/agent-memory-llm - repo: https://github.com/reaatech/agent-memory ## @reaatech/agent-memory-policies **Category:** Domain Pipelines · **Repo:** agent-memory · **Status:** published v0.1.0 A policy engine for memory lifecycle management that provides decay scoring, forgetting decisions, and contradiction resolution, exposed as a `PolicyEngine` class that composes `DecayEngine`, `ForgettingPolicy`, `ContradictionDetector`, and `ContradictionResolver` with pluggable rules. - npm: https://www.npmjs.com/package/@reaatech/agent-memory-policies - detail: https://reaatech.com/products/domain-pipelines/agent-memory/packages/agent-memory-policies - repo: https://github.com/reaatech/agent-memory ## @reaatech/agent-memory-retrieval **Category:** Domain Pipelines · **Repo:** agent-memory · **Status:** published v0.1.0 A semantic memory retriever for LLM agents that combines embedding similarity with recency, importance, and topic diversification, exposing a `MemoryRetriever` class with pluggable ranking strategies and a `ContextInjector` for formatting results into prompts with token budgeting. Requires a memory storage backend and an embedding provider at runtime. - npm: https://www.npmjs.com/package/@reaatech/agent-memory-retrieval - detail: https://reaatech.com/products/domain-pipelines/agent-memory/packages/agent-memory-retrieval - repo: https://github.com/reaatech/agent-memory ## @reaatech/agent-memory-storage **Category:** Domain Pipelines · **Repo:** agent-memory · **Status:** published v0.1.0 A `MemoryStorage` interface (class) with 14 methods for CRUD, batch operations, similarity search, metadata filtering, health checks, and backup/restore of agent memories, plus two implementations: a zero-dependency in-memory adapter for testing and a PostgreSQL pgvector adapter for production that requires the `pg` package. - npm: https://www.npmjs.com/package/@reaatech/agent-memory-storage - detail: https://reaatech.com/products/domain-pipelines/agent-memory/packages/agent-memory-storage - repo: https://github.com/reaatech/agent-memory ## @reaatech/media-pipeline-mcp-anthropic **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 An Anthropic provider for the media pipeline framework that wraps Claude Sonnet's vision models to perform image description, OCR, table extraction, structured field extraction, and document summarization. It exports an `AnthropicProvider` class with an `execute()` method that accepts an operation name and parameters, and supports streaming token-by-token responses for all text-shaped operations. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-anthropic - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-anthropic - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-audio-gen **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A factory function that creates an `AudioGenOperations` instance providing text-to-speech, speech-to-text, speaker diarization, source separation, music generation, and sound effects, with automatic multi-provider routing to OpenAI, ElevenLabs, Deepgram, or any conformant provider. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-audio-gen - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-audio-gen - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-comfyui **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A ComfyUI provider for the media pipeline framework that runs image generation, image editing, and video generation on your own GPU via local ComfyUI workflows, with zero API cost. It exports a `ComfyUIProvider` class that accepts a `baseUrl` pointing to a running ComfyUI instance and optionally a `workflowsDir` for custom JSON workflows. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-comfyui - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-comfyui - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-core **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 Core framework for media pipeline orchestration, providing a Zod-validated type system, pipeline execution engine with variable interpolation, quality gate evaluation, artifact registry, budget enforcement, persistence-based resume, cost tracking, event bus, and a configurable mock provider for testing. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-core - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-core - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-cost **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A typed cost ledger for tracking per-operation expenses in a media pipeline, providing an `InMemoryCostLedger` class with `charge()`, `preflight()`, `totalForRun()`, and `totalForTenant()` methods that support USD micro-precision, run-scoped and tenant-scoped queries, and preflight budget checks. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-cost - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-cost - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-deepgram **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.4.0 A Deepgram provider for the media-pipeline framework that exposes `audio.stt` and `audio.diarize` operations via a `DeepgramProvider` class, using Nova-2 for speech-to-text transcription with smart formatting, speaker diarization, and WebSocket streaming support. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-deepgram - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-deepgram - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-doc-extraction **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A factory function (`createDocumentExtractionOperations`) that returns a `DocumentExtractionOperations` instance providing OCR, table extraction, schema-driven field extraction, and content summarization, delegating each operation to registered LLM providers (e.g., Google, Anthropic, OpenAI) with automatic fallback chains. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-doc-extraction - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-doc-extraction - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-elevenlabs **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 An ElevenLabs provider for the media pipeline framework that exposes a `MediaProvider` class (`ElevenLabsProvider`) with `execute`, `healthCheck`, and `estimateCost` methods for generating text-to-speech audio with configurable voice, speed, model, and output format. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-elevenlabs - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-elevenlabs - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-fal **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A Fal.ai provider for the media pipeline framework that exposes a `FalProvider` class supporting image generation, upscaling, background removal, text-to-video, and image-to-video operations via the fal.ai API, with native webhook support and streaming queue events for long-running tasks. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-fal - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-fal - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-google **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.4.0 A Google Cloud provider for the media-pipeline framework that exposes Document AI (OCR, table extraction, field extraction) and Vertex AI Gemini (image description) as a unified set of operations via an `execute` method on the `GoogleProvider` class. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-google - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-google - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-image-edit **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 An image editing operations factory that provides Sharp-based local processing (resize, crop, composite) and provider-delegated operations (upscale, background removal, inpainting, image description) through a multi-provider routing system. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-image-edit - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-image-edit - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-keyvault **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 Multi-tenant API key vault that resolves tenant-scoped provider credentials from AWS Secrets Manager, GCP Secret Manager, environment variables, or in-memory storage, exposing `resolve()`, `get()`, and `health()` methods with LRU TTL caching. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-keyvault - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-keyvault - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-luma **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A Luma AI provider for the media pipeline framework that generates 3D meshes from text descriptions via the Dream Machine API, exposing a `LumaProvider` class with `execute()`, `healthCheck()`, and `estimateCost()` methods for text-to-3D generation in GLB and USDZ formats. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-luma - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-luma - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-meshy **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A Meshy-4 provider for the media-pipeline framework that generates 3D meshes from text prompts or reference images, supporting PBR textures and GLB/FBX/OBJ/USDZ output formats. It exports a `MeshyProvider` class that implements the `MediaProvider` interface for use with the `@reaatech/media-pipeline-mcp` framework. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-meshy - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-meshy - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-observability **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 Provides a single `ObservabilityService` facade that bundles OpenTelemetry tracing with auto-instrumentation, Prometheus-compatible metrics, structured Pino-compatible logging, and in-memory cost reporting, all configurable via a single `ObservabilityConfig` object. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-observability - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-observability - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-ollama **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A local Ollama provider for the media-pipeline framework that exposes text completion, embedding generation, and image description via any Ollama model. It provides an `OllamaProvider` class implementing the `MediaProvider` interface, requiring a running Ollama instance at a configurable `baseUrl`. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-ollama - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-ollama - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-openai **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 An OpenAI provider for the media-pipeline framework that exposes a class (`OpenAIProvider`) supporting DALL-E 3 image generation, GPT-4o vision-based image description, TTS-1 text-to-speech, and Whisper-1 speech-to-text transcription via the OpenAI REST API with no SDK dependency. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-openai - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-openai - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-persistence **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 Provides in-memory and Redis-backed pipeline state store abstractions with optimistic locking, run lifecycle management, event log persistence, and tenant-scoped queries for multi-tenant pipeline orchestration. Exports `InMemoryPipelineStateStore` and `RedisPipelineStateStore` classes; the Redis implementation requires the `ioredis` peer dependency. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-persistence - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-persistence - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-pipeline **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A set of functions for creating, validating, and executing media processing pipelines with pre-built templates, variable interpolation, batch processing, aspect-ratio fan-out, and quality gates (loudness normalization, content safety classification). It exports a `PipelineOperations` class that depends on an `ArtifactRegistry` from `@reaatech/media-pipeline-mcp-core`. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-pipeline - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-pipeline - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-provenance **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A C2PA content provenance signing library for AI-generated media that embeds tamper-evident manifests naming the model, pipeline DAG, and operator. Exports a `ProvenanceSigner` class that accepts a `ProvenanceManifest` and returns signed artifacts with either sidecar JSON manifests or in-file C2PA embedding via `c2pa-node`, supporting signing keys from PEM files, AWS KMS, GCP KMS, or Azure Key Vault. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-provenance - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-provenance - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-provider-core **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 Abstract base class and shared interfaces for media provider implementations, providing a `MediaProvider` abstract class with deterministic caching, retry with exponential backoff, cost estimation, and a multi-strategy router for provider selection across health, budget, and latency constraints. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-provider-core - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-provider-core - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-replicate **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.4.0 A Replicate provider for the media-pipeline framework that exposes image upscaling, background removal, inpainting, audio source separation, text-to-video, and image-to-video operations as a class with an `execute` method, requiring a Replicate API key at runtime. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-replicate - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-replicate - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-resilience **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A three-state circuit breaker and retry policy with exponential backoff and jitter for protecting downstream media pipeline providers from cascading failures. Provides `createCircuitBreaker(name, config)` and `createRetryPolicy(config)` factory functions that return classes with `execute(fn)` methods, plus typed error classes (`CircuitBreakerError`, `MaxRetriesExceededError`) and live stats reporting. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-resilience - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-resilience - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-security **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 Provides authentication (API keys with constant-time comparison, JWT/OAuth2 with HS256), role-based access control (admin/operator/viewer with 10 permissions), token bucket rate limiting, and audit logging with SIEM export for media pipeline deployments. Exports `AuthMiddleware`, `createRateLimiter`, and `createAuditLogger` classes/factories. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-security - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-security - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-server **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.1 An MCP server that exposes 35+ media operations (image generation/editing, audio TTS/STT, video generation, document extraction, 3D mesh generation) as JSON-RPC 2.0 tools over StreamableHTTP transport, with built-in provider routing, cost tracking, pipeline execution, quality gates, webhooks, and multi-tenant key management. It provides a CLI binary (`media-pipeline-mcp`) and depends on `@modelcontextprotocol/sdk` for MCP protocol compliance, with provider auto-detection from environment variables (`OPENAI_API_KEY`, `STABILITY_API_KEY`, etc.). - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-server - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-server - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-stability **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A Stability AI provider for the media pipeline framework that generates images via the Stable Image v2beta REST API using SD3, SDXL, and SD1.5 models, exposing a `StabilityProvider` class with `execute`, `healthCheck`, and `estimateCost` methods. It depends on the `@reaatech/media-pipeline-mcp` framework and uses the native Fetch API with no SDK dependency. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-stability - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-stability - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-storage **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A unified `ArtifactStore` interface (`put`, `get`, `getSignedUrl`, `delete`, `list`, `healthCheck`) backed by local filesystem, AWS S3, or Google Cloud Storage, selected via a type-safe `createStorage` factory function. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-storage - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-storage - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/media-pipeline-mcp-video-gen **Category:** Domain Pipelines · **Repo:** media-pipeline-mcp · **Status:** published v0.3.0 A factory function (`createVideoGenOperations`) that returns a `VideoGenOperations` instance for text-to-video and image-to-video generation via pluggable providers (e.g., Replicate), plus local ffmpeg-based frame extraction, audio extraction, subtitle generation with burn-in, loudness normalization, and video cropping. Requires an `ArtifactRegistry` and `ArtifactStore` at construction, and ffmpeg installed on the host for local processing operations. - npm: https://www.npmjs.com/package/@reaatech/media-pipeline-mcp-video-gen - detail: https://reaatech.com/products/domain-pipelines/media-pipeline-mcp/packages/media-pipeline-mcp-video-gen - repo: https://github.com/reaatech/media-pipeline-mcp ## @reaatech/create-voice-agent **Category:** Domain Pipelines · **Repo:** voice-agent-kit · **Status:** published v0.1.0 A scaffolding CLI that generates a complete voice-agent-kit project with pipeline configuration, STT/TTS provider setup, telephony or WebRTC transport, an MCP client, and a ready-to-run server. - npm: https://www.npmjs.com/package/@reaatech/create-voice-agent - detail: https://reaatech.com/products/domain-pipelines/voice-agent-kit/packages/create-voice-agent - repo: https://github.com/reaatech/voice-agent-kit ## @reaatech/voice-agent-core **Category:** Domain Pipelines · **Repo:** voice-agent-kit · **Status:** published v0.1.0 A Zod-validated configuration system and pipeline orchestrator for building voice-enabled AI agents, providing a `createPipeline()` function that coordinates STT, MCP, and TTS stages with latency enforcement, session management, and OpenTelemetry observability. - npm: https://www.npmjs.com/package/@reaatech/voice-agent-core - detail: https://reaatech.com/products/domain-pipelines/voice-agent-kit/packages/voice-agent-core - repo: https://github.com/reaatech/voice-agent-kit ## @reaatech/voice-agent-mcp-client **Category:** Domain Pipelines · **Repo:** voice-agent-kit · **Status:** published v0.1.0 A JSON-RPC 2.0 client that connects to any MCP server endpoint, providing tool discovery, conversation history management, retry with backoff, and TTS-safe response sanitization. It exposes an `MCPClient` class with `connect()`, `sendRequest()`, `discoverTools()`, and `close()` methods, and requires only a `fetch`-compatible runtime. - npm: https://www.npmjs.com/package/@reaatech/voice-agent-mcp-client - detail: https://reaatech.com/products/domain-pipelines/voice-agent-kit/packages/voice-agent-mcp-client - repo: https://github.com/reaatech/voice-agent-kit ## @reaatech/voice-agent-simulator **Category:** Domain Pipelines · **Repo:** voice-agent-kit · **Status:** published v0.1.1 A CLI and programmatic simulator that runs a voice agent pipeline (STT → MCP → TTS) locally from a WAV file or live microphone, reporting per-turn latency without requiring Twilio or cloud telephony. Exports `createSimulator`, `Simulator`, `renderLatencyWaterfall`, `readWavFile`, `writeWavFile`, `captureMicrophone`, and `playAudio`. - npm: https://www.npmjs.com/package/@reaatech/voice-agent-simulator - detail: https://reaatech.com/products/domain-pipelines/voice-agent-kit/packages/voice-agent-simulator - repo: https://github.com/reaatech/voice-agent-kit ## @reaatech/voice-agent-stt **Category:** Domain Pipelines · **Repo:** voice-agent-kit · **Status:** published v0.1.1 Provider-agnostic speech-to-text interface with a unified `STTProvider` class and seven adapter implementations (Deepgram, AWS Transcribe, Google Cloud Speech-to-Text, OpenAI Realtime, OpenAI Whisper, AssemblyAI, Groq Whisper), plus built-in audio format conversion between mulaw and linear16 with sample rate resampling. - npm: https://www.npmjs.com/package/@reaatech/voice-agent-stt - detail: https://reaatech.com/products/domain-pipelines/voice-agent-kit/packages/voice-agent-stt - repo: https://github.com/reaatech/voice-agent-kit ## @reaatech/voice-agent-telephony **Category:** Domain Pipelines · **Repo:** voice-agent-kit · **Status:** published v0.1.1 A WebSocket handler for voice AI agents that normalizes bidirectional streaming protocols (start/media/stop/mark/DTMF) across Twilio, Telnyx, SignalWire, and Vonage, providing barge-in detection, audio buffering, and base64 encoding/decoding. Exports a `TwilioMediaStreamHandler` class (EventEmitter) with methods like `acceptConnection`, `sendAudio`, `clearAudio`, and `sendMark`, plus static `encodeForTwilio`/`decodeFromTwilio` utilities. - npm: https://www.npmjs.com/package/@reaatech/voice-agent-telephony - detail: https://reaatech.com/products/domain-pipelines/voice-agent-kit/packages/voice-agent-telephony - repo: https://github.com/reaatech/voice-agent-kit ## @reaatech/voice-agent-tts **Category:** Domain Pipelines · **Repo:** voice-agent-kit · **Status:** published v0.1.1 Provider-agnostic text-to-speech interface with five adapter implementations (Deepgram Aura, AWS Polly, Google Cloud TTS, ElevenLabs, Cartesia), returning streaming audio as `AsyncIterable` with cancelable synthesis and Twilio-ready audio formatting. - npm: https://www.npmjs.com/package/@reaatech/voice-agent-tts - detail: https://reaatech.com/products/domain-pipelines/voice-agent-kit/packages/voice-agent-tts - repo: https://github.com/reaatech/voice-agent-kit ## @reaatech/voice-agent-webrtc **Category:** Domain Pipelines · **Repo:** voice-agent-kit · **Status:** published v0.1.1 A WebSocket-based transport class (`WebRTCTransport`) for browser voice AI agents that handles Opus encode/decode, PCM resampling, and barge-in detection, paired with standalone PCM utility functions. Requires a WebSocket connection and optionally `@discordjs/opus` or `prism-media` for Opus support. - npm: https://www.npmjs.com/package/@reaatech/voice-agent-webrtc - detail: https://reaatech.com/products/domain-pipelines/voice-agent-kit/packages/voice-agent-webrtc - repo: https://github.com/reaatech/voice-agent-kit