topoteretes/cognee
Knowledge Engine for AI Agent Memory in 6 lines of code
This project helps AI developers build intelligent agents that can remember and learn over time. You provide the AI with documents or other data, and it processes this information to create a dynamic knowledge base. The output is an AI agent that can provide relevant context, answer complex questions, and even share knowledge with other agents, making it ideal for creating more effective AI applications.
13,204 stars. Actively maintained with 585 commits in the last 30 days. Available on PyPI.
Use this if you are building AI agents and need a way for them to persistently store, learn from, and retrieve information from various data sources.
Not ideal if you are looking for a simple keyword search tool or don't intend to build AI agents that require complex memory and learning capabilities.
Stars
13,204
Forks
1,336
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
585
Dependencies
43
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/topoteretes/cognee"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Recent Releases
Related tools
CaviraOSS/OpenMemory
Local persistent memory store for LLM applications including claude desktop, github copilot,...
verygoodplugins/automem
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory:
CortexReach/memory-lancedb-pro
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder...
divagr18/memlayer
Plug-and-play memory for LLMs in 3 lines of code. Add persistent, intelligent, human-like memory...
verygoodplugins/mcp-automem
AutoMem is a graph-vector memory service that gives AI assistants durable, relational memory: