jeffpierce/memory-palace

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

41
/ 100
Emerging

This project helps AI agents remember and recall information across different sessions and providers, overcoming the limitation of short-term memory in AI models. It takes in facts, decisions, insights, and conversation context, storing them as persistent memories. When you need that information again, it lets you search for it by meaning, not just keywords, and outputs relevant memories for your AI to use. This is for anyone using AI agents for ongoing tasks, like researchers, customer service bots, or project managers, who need their AI to build and retain knowledge over time.

Use this if your AI agents need a reliable, long-term memory system to retain context, decisions, and knowledge across multiple sessions or different AI providers.

Not ideal if you only need short-term context for single-session AI interactions or if you are locked into a proprietary AI ecosystem that provides its own sufficient memory solution.

AI agent memory Persistent knowledge Context management Semantic search Knowledge graph
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.