jeffpierce/memory-palace

Persistent memory system for agentic AI via MCP - remember, recall, forget with semantic search with knowledge graph

41
/ 100
Emerging

Implements centrality-weighted retrieval that combines semantic similarity with access frequency and graph importance, plus multi-instance pub/sub messaging built directly into the memory layer. Runs entirely locally via Ollama for embeddings and LLM operations, with support for both SQLite (personal) and PostgreSQL+pgvector (team) backends, and integrates natively with any MCP-compatible client through 13 tools including semantic code search via prose descriptions rather than raw token matching.

No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 11 / 25
Community 13 / 25

How are scores calculated?

Stars

31

Forks

5

Language

Python

License

MIT

Last pushed

Feb 15, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/jeffpierce/memory-palace"

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