Memwright

Embedded memory for AI agents with SQLite, pgvector semantic search, and Neo4j graph traversal fused via Reciprocal Rank Fusion.

Provides persistent memory for AI agents using a three-layer retrieval system combining SQLite storage, pgvector semantic search, and Neo4j entity graph traversal. Results are ranked using Reciprocal Rank Fusion for token-efficient recall at 300-500 tokens per query. Supports contradiction detection, entity timeline tracking, and runs fully locally via Docker with integrations for Claude Code, Cursor, and direct Python library usage.