verygoodplugins/automem
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:
**Combines FalkorDB graph storage with Qdrant vectors to enable hybrid semantic and relational search**, allowing AI to retrieve not just relevant memories but the relationships and reasoning between them. Implements research-backed techniques including multi-hop bridge discovery, automatic entity extraction with 11+ relationship types, and consolidation pipelines for pattern detection. Deploys as a standalone Flask service with sub-100ms recall performance and includes benchmarked baselines (87-89% on LoCoMo), making it suitable for long-term AI assistant memory in production environments.
659 stars. Actively maintained with 18 commits in the last 30 days.
Stars
659
Forks
80
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
18
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/verygoodplugins/automem"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
topoteretes/cognee
Knowledge Engine for AI Agent Memory in 6 lines of code
divagr18/memlayer
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory...
CortexReach/memory-lancedb-pro
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder...
CaviraOSS/OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot,...
verygoodplugins/mcp-automem
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory: