reaatech/agent-memory

These packages provide a managed long-term memory layer for AI agents, handling the extraction, storage, and retrieval of facts and preferences. You would adopt them to move beyond simple vector search by implementing active lifecycle management, including automated decay, contradiction resolution, and importance-based retention. The system is built as a modular set of providers and policies, allowing you to swap storage backends like PostgreSQL or integrate custom retention rules while maintaining a unified interface for agent state.