gannonh/memento-mcp

Memento MCP: A Knowledge Graph Memory System for LLMs

58
/ 100
Established

Implements a Neo4j-backed knowledge graph with semantic search via vector embeddings, temporal versioning, and confidence-weighted relations for persistent LLM memory across MCP-compatible clients. Supports hybrid search combining vector similarity with keyword matching, automatic schema initialization, and point-in-time graph retrieval for tracking historical knowledge evolution. Integrates directly with Claude Desktop, Cursor, and GitHub Copilot through the Model Context Protocol.

408 stars and 75 monthly downloads. Available on npm.

Maintenance 6 / 25
Adoption 14 / 25
Maturity 18 / 25
Community 20 / 25

How are scores calculated?

Stars

408

Forks

63

Language

TypeScript

License

MIT

Last pushed

Oct 27, 2025

Monthly downloads

75

Commits (30d)

0

Dependencies

8

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/gannonh/memento-mcp"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.