cedricvidal/memorious-mcp

Semantic Memory for MCP. 100% Local & Private. Store, recall, and forget with vector search via ChromaDB

43
/ 100
Emerging

Implements three core tools (`store`, `recall`, `forget`) built on FastMCP's stdio transport, with ChromaDB handling vector embeddings locally for semantic similarity search. Supports folder-scoped memory isolation ideal for VS Code and Claude agents, using disk-based persistent storage in a `.memorious` directory with configurable paths. Requires Python 3.12+ and processes all embeddings locally—no external API calls or cloud dependencies.

No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 2 / 25
Adoption 8 / 25
Maturity 18 / 25
Community 15 / 25

How are scores calculated?

Stars

8

Forks

4

Language

Python

License

MIT

Last pushed

Oct 01, 2025

Monthly downloads

80

Commits (30d)

0

Dependencies

4

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/cedricvidal/memorious-mcp"

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