Mnemon

Persistent layered memory for AI agents with local-first SQLite storage.

Mnemon provides structured long-term memory for AI agents through four memory layers: episodic (events and sessions), semantic (facts and preferences), procedural (rules and workflows), and resource (reference material). Stores everything in a single SQLite database file with FTS5 search and optional vector embeddings. Includes fact versioning through superseding chains, multi-language stemming support, and comprehensive MCP tools for memory management.