M3 Memory
Persistent memory layer for AI agents with hybrid search, contradiction detection, and knowledge graphs.
M3 Memory provides a persistent memory layer for MCP agents, enabling facts, decisions, and preferences to survive across sessions through local storage. Supports hybrid search combining full-text, vector similarity, and diversity re-ranking, automatic contradiction detection with bitemporal versioning, knowledge graph linking across 8 relationship types, GDPR compliance tools, and cross-device sync across SQLite, PostgreSQL, and ChromaDB backends.
Source
Repository: https://github.com/skynetcmd/m3-memory
Maintain M3 Memory?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/mcp/skynetcmd-m3-memory?ref=badge) Related mcp
Wikipedia Provides a structured interface for searching and retrieving Wikipedia articles in clean Markdown format, enabling access to up-to
Remembra Persistent memory layer with entity resolution, temporal decay, and graph-aware recall.
Memwright Embedded memory for AI agents with SQLite, pgvector semantic search, and Neo4j graph traversal fused via Reciprocal Rank Fusion.
French Tax Integrates with official French tax websites (impots.gouv.fr, service-public.fr, legifrance.gouv.fr) to provide tax calculations,
Remem Local-first automatic memory for Claude Code and Codex: capture, distill, and recall from SQLite.
Replicate Integrates with Replicate API to provide seamless access to diverse machine learning models for inference and result retrieval acr