clawdbrunner/openclaw-graphiti-memory

Hybrid memory system for OpenClaw using Graphiti temporal knowledge graph

38
/ 100
Emerging

It provides a three-layered memory architecture: private agent files (QMD), shared reference files (symlinked), and a shared knowledge graph for temporal facts and cross-agent queries. Agents interact with this system through dedicated `graphiti-search`, `graphiti-log`, and `graphiti-context` shell scripts. The project integrates with OpenClaw, utilizing Docker for Graphiti and Neo4j, and requires an OpenAI API key for embeddings during ingestion.

No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 11 / 25
Community 9 / 25

How are scores calculated?

Stars

57

Forks

4

Language

Shell

License

MIT

Last pushed

Feb 08, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/clawdbrunner/openclaw-graphiti-memory"

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