Agent memory is having a moment, and Cognee just rode it to 23.7k GitHub stars — up 700+ in a single day. It’s an open-source long-term memory layer that gives AI agents persistent recall across sessions, instead of stuffing everything back into the context window.
What it actually does
Feed Cognee your data in any format. It runs an ingest pipeline that fuses vector embeddings, graph reasoning, and cognitive-science ontologies into a knowledge graph — searchable by meaning, connected by relationships. The pitch that’s landing: run the whole thing on a single Postgres instance. No separate graph database, vector store, and session store to babysit.
The API and who it’s for
Four operations cover it: remember, recall, forget, improve. Queries auto-route to the best retrieval strategy. Official clients ship for Python, Rust, and TypeScript, plus a hosted Cognee Cloud. Enterprise adds user isolation, audit logs, and traceability.
The Berlin team raised a €7.5M seed (Redalpine, 7percent Ventures) and claims 70+ companies already running it in production.
You Might Also Like
- Openviking Treats ai Agent Memory Like a File System and 9k Github Stars say its Working
- Tradingagents 33k Stars for an Open Source Framework That Simulates an Entire Trading Firm With llm Agents
- Onyx Hits 19 7k Github Stars the Open Source Answer to Gleans 7 2b Enterprise ai Play
- Agent Reach Hits 12k Github Stars by Solving ai Agents Biggest Blind Spot
- Mentra Live Mentraos Open Source hit Github one Typescript sdk Four Pairs of Glasses
Top AI Product 
Leave a comment