Technoculture/personal-graph
Simple Graph Memory for AI applications
Built on libsql (a Rust-based SQLite engine) with vector search via sqlite-vss, it enables semantic graph queries through natural language while supporting both cloud (Turso) and local execution. Integrates with DSPy for retrieval-augmented generation, Ollama for local LLMs, and exports to PyG/NetworkX for graph neural network applications. Combines structured entity-relationship storage with semantic embeddings to handle both working memory (contextual retrieval) and long-term memory (temporal/attribute-based filtering) in AI systems.
Stars
91
Forks
11
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 23, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/Technoculture/personal-graph"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
topoteretes/cognee
Knowledge Engine for AI Agent Memory in 6 lines of code
CaviraOSS/OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot,...
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...
verygoodplugins/automem
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory: