🚀 Our new case-study with Bayer is out.Get it here 🔬🧬
FAQ
Common questions about cognee, AI memory infrastructure, deployment, and getting started.
What is cognee?+cognee is an open-source AI memory engine that turns data into a queryable knowledge graph for agents and LLM applications.What can I build with cognee?+Teams use cognee to build agent memory, GraphRAG pipelines, semantic search, document intelligence, customer support agents, and internal copilots that need persistent context.How is cognee different from a vector database or basic RAG?+A vector database retrieves similar chunks. cognee combines vectors with graph relationships, generated data models, and memory operations so agents can retrieve connected context and reason across sources.Is cognee open source?+Yes. The cognee SDK is open source on GitHub, and teams can also use hosted Cognee Cloud or enterprise deployment options.Can I run cognee locally or self-host it?+Yes. cognee can run locally for development and can be self-hosted for teams that need infrastructure control, private deployments, or stricter data boundaries.Which databases and data sources does cognee support?+cognee supports common document and data formats, and can work with graph and vector storage backends such as Kuzu, NetworkX, Neo4j, FalkorDB, LanceDB, Qdrant, Milvus, Redis, and related infrastructure.Where should I start?+Start with the product page for the platform overview, the docs for implementation details, or the blog and academy for deeper guides on AI memory, knowledge graphs, and agent infrastructure.How does pricing work?+The pricing page lists the current self-serve plans and enterprise options. Open-source usage is available separately from hosted Cognee Cloud plans.How can I talk to the cognee team?+Use the contact options on the site for partnerships, custom deployments, enterprise questions, or implementation support.