cognee
topoteretes/cognee
Memory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources.
- Local integrations
Installation, supported tools and required credentials are maintained by the project.
Project details
- GitHub stars
- 32,632
- Language
- Python
- License
- Apache-2.0
- Forks
- 3,393
- Latest release
- v1.6.55d ago
- Activity
- updated today
- ai
- cognitive-architecture
- vector-database
- ai-agents
- graph-database
- ai-memory
- cognitive-memory
- knowledge
First MCP server?Start with the basics
Knowledge graph-based persistent memory for maintaining context.
Up-to-date code documentation for LLMs and AI code editors.
Hindsight: long-term memory for AI agents modeled on human memory.
Turn docs, GitHub repos, PDFs, videos, Confluence, Notion and Slack/Discord into AI skills and RAG knowledge, exportable to vector databases like Qdrant.
Local-first AI memory: a semantic knowledge graph of Markdown files that humans and LLMs both read and write, with optional cloud sync and team workspaces.
Self-hosted Markdown knowledge base with a web UI: search, read, create, edit, tag and template notes.
Universal memory agent for AI: provides semantic search, namespace management, text/vector operations and RAG for local or remote environments.
Memory service with semantic search, persistent storage and autonomous memory consolidation.