gh9ko8y /
graphmemory
Bitemporal AI memory system: six-variable decay, time-graded recall, TTL expiry, dedupe, competitive retrieval (Neo4j + PostgreSQL + Redis)
Updated 41 min ago
Maintain this repo? Add this badge to your README.
Why now
+112 stars gained this week
Stars gained each day, last 30 days
Oct 4Oct 19Today
This week Before
In short
It needs Python 3.10+, Docker Compose to run Neo4j, PostgreSQL and Redis, and an LLM API key set via environment variables. It is used as an MCP server or a local HTTP service that AI agents call.
Summary written by AI from the repository’s description and README.
gh9ko8y / graphmemory
View on GitHub(opens in new tab)