{"id":"cognee","name":"Cognee","maker":"Cognee","url":"https://www.cognee.ai","repo":"topoteretes/cognee","docs":"https://docs.cognee.ai","package":"pypi:cognee","summary":"An open source engine that turns documents and data into a knowledge graph with vectors for agent memory.","details":"Cognee ingests files and other sources, builds a graph and embeddings from them, and answers queries over both. It is a Python library with a command-line tool and an MCP server, and it can use several graph, vector and relational stores. The maker also runs a hosted version.","open_source":true,"hosted":true,"speaks":["mcp"],"also":["retrieval"],"verified":"2026-11-15","category":"memory","category_name":"Agent memory","page":"https://modelmoot.com/tools/cognee","reviewed":"2026-11-15","checked":{"at":"2026-11-15T13:03:28.711Z","address_answers":true,"repository":{"at":"2026-11-15T19:19:09.346Z","archived":false,"licence":"Apache-2.0","language":"Python","last_change":"2026-11-15T18:20:52.000Z","latest_release":{"tag":"v1.6.8","published":"2026-11-12T22:31:22.000Z"}}},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}