Reliability & Ops

These packages give you a CLI, library, and MCP server that scan a service repository and produce a complete operator runbook—alerts, dashboards, failure modes, rollback steps, incident workflows, health checks, and dependency maps. You would adopt them to automate the creation and maintenance of runbooks for every service in your organization, replacing manual documentation that goes stale. The packages are designed as independent, composable modules (analyzer, alerts, dashboards, etc.) that share core types and Zod schemas, so you can use the full pipeline via the CLI or pick individual packages for programmatic use.

These packages give you a circuit breaker designed specifically for agent-to-tool and agent-to-agent communication, with per-tool circuit isolation, confidence-aware tripping, and cost-based rate limiting. You would adopt them to prevent cascading failures when an LLM agent repeatedly calls a degraded tool, or to automatically route traffic away from expensive or unreliable model endpoints. The most distinctive thing is that circuits are identified by a logical `circuitId` (not a hostname), and the state machine uses a lazy auto-transition model with no timers, plus optional leader-elected persistence across restarts via Firestore, DynamoDB, or Redis.

These packages give you idempotency middleware for POST, PUT, and PATCH requests — duplicate requests with the same `Idempotency-Key` header return the cached original response instead of re-executing side effects. You'd adopt them to safely retry payment charges, webhook deliveries, or any mutation where duplicate execution would cause data corruption or duplicate charges. The core provides a pluggable `StorageAdapter` interface with in-memory, Redis, DynamoDB, and Firestore backends, plus framework adapters for Express, Koa, and a generic handler for Lambda or gRPC, all with built-in distributed locking that prevents concurrent handler execution for the same key.

These packages give you a zero-downtime secret rotation engine that orchestrates the full lifecycle—generate, propagate, verify, activate, and revoke—across AWS Secrets Manager, GCP Secret Manager, HashiCorp Vault, and Vercel environment variables. You'd adopt them to solve the operational problem of rotating secrets in production without causing outages when consumers haven't picked up the new key yet. The most distinctive thing is the overlapping key window design combined with dual verification strategies (provider-level polling and consumer-level active verification), all exposed through a pluggable provider interface and an optional HTTP sidecar that runs with zero code.

These packages give you a complete session management layer for multi-turn AI agent conversations, handling conversation history windowing, token budget enforcement, context compression, and agent handoff. You'd adopt them to avoid rebuilding the same session lifecycle logic—create, update, end, delete, and list sessions with participants and messages—that every agent system needs. The most distinctive thing is the pluggable storage adapter interface with production backends for Firestore, DynamoDB, and Redis, each implementing optimistic concurrency with version-checked writes and deterministic message ordering, plus three compression strategies (sliding window, summarization, hybrid) with cached summaries so the summarizer isn't re-invoked on every fetch.

These packages give you a repair engine that takes a Zod schema and malformed LLM output, then runs it through six graduated strategies—stripping markdown fences, extracting JSON from prose, fixing syntax errors, coercing types, fuzzy-matching keys, and removing extra fields—to return valid, schema-conforming data instead of crashing. You'd adopt them to handle the common failure modes of LLM structured output generation: trailing commas, truncated streams, Python literals, hallucinated field names, and JSON buried in conversational wrappers. The most distinctive thing is the graduated pipeline approach—each strategy runs in sequence, the engine validates after each step, and it returns as soon as the data conforms, giving you detailed diagnostics including per-field errors and best-effort partial data when full repair fails.