Cognee
An open-source memory platform that turns documents, code and conversations into a knowledge graph for agents.
Sources and review
Checked against public documentation on . Suitability guidance is our editorial judgment; this is not a performance benchmark or an endorsement.
Agents whose memory should be structured around entities and relationships rather than a flat vector store.
About Cognee
Cognee gives AI agents persistent long-term memory by turning documents, code and conversations into a self-hosted knowledge graph they can search and reuse across sessions. It can start locally without an OpenAI or Anthropic key, using local extraction and embedding models, supports custom data models and ontologies, and targets uses from a shared company-wide memory to memory that carries between agent runs.
Cognee is listed in this index written primarily in Python, with 33k stars on GitHub. Its latest recorded repository push was in November 2026; that is not an ASE editorial review date.
uv pip install "cognee[gliner]"Cognee and related category tools
Alternatives guide →| Record | Stars | Pricing | ||
|---|---|---|---|---|
| Cogneethis listing | 33k | Python | Apache-2.0 | Costs not checked |
| Graphiti | 32k | Python | Apache-2.0 | Costs not checked |
| Mistral Search Index | — | — | — | Pricing not verified; check storage, query, embedding and extraction charges |
| byterover-cli | 4.9k | TypeScript | — | Costs not checked |
| XCrawl | — | — | — | Paid product |
| Vectoree | — | — | — | Freemium |
