GitHub
FreeBuild AI memory with a Memory Platform that learns
About GitHub
Cognee is an open-source memory platform for AI agents that enables persistent long-term memory across sessions. It ingests data in any format or structure and continuously learns to provide the right context for AI agents. The platform combines vector search, graph databases, and cognitive science approaches to make documents searchable by meaning and connected by relationships as they evolve. It includes features such as unified ingestion, graph/vector search, local deployment, ontology grounding, multimodal support, learning from feedback, context management, cross-agent knowledge sharing, agentic user/tenant isolation, traceability, OpenTelemetry (OTEL) collector, and audit traits. Cognee can be deployed on self-hosted infrastructure or in any cloud, with a hosted cloud option available.
Key Features
Pros & Cons
- Open-source and self-hostable, giving full control over data
- Combines vector search and graph database approaches for richer context
- Supports continuous learning from agent feedback
- Includes built-in traceability and audit capabilities
- Requires infrastructure setup for self-hosted deployment
- Relatively new project with evolving documentation