Last updated 06-30-2026
Category:
Reviews:
Join thousands of AI enthusiasts in the World of AI!
Cognee
Cognee is an open-source memory platform for LLM agents. It captures context from documents, chats, and APIs, turns that material into graph memory, and lets agents recall it across sessions instead of starting from scratch each run.
Where basic RAG pulls similar text chunks, Cognee links entities and facts in a knowledge graph and pairs that structure with vector search. The SDK centers on four verbs: remember, recall, forget, and improve. The same surface is available over HTTP and MCP, so coding agents like Claude Code or Codex can share one durable memory layer.
Teams use it for coding agent memory, GraphRAG pipelines, deal intelligence, research archives, and customer-facing agents that need cited answers. You can run it locally with pip, self-host in Docker or on-prem, or move to Cognee Cloud when you want managed scale. The project reports 26k+ GitHub stars and 5M+ SDK runs per month, with production deployments at companies including Bayer and Knowunity.
pip install cognee and connect Claude Code, Codex, or any MCP client in minutes
remember, recall, forget, and improve as the core memory API across SDK, HTTP, and MCP
Hybrid graph and vector memory links entities and facts across long conversations
Memory improves from real agent usage instead of staying static after ingestion
@cognee.agent_memory decorator composes graph and session memory for async agents
Ingest from S3, Slack, Notion, Google Drive, and other adapters into one recall layer
Self-host locally, in Docker, on-prem, or scale on managed Cognee Cloud
Open-source core lets you run the full memory engine locally or self-hosted without vendor lock-in.
Graph plus vector memory retrieves connected context instead of isolated chunks.
Strong adoption signals with 26k+ GitHub stars and published BEAM benchmark results.
MCP and SDK integrations fit existing agent workflows like Claude Code and Codex.
Free cloud tier includes 1M tokens and one workspace with no credit card required.
Standard plan workspace add-ons cost $5 each per month on top of token usage.
Enterprise features such as dedicated support and BYO cloud require a sales conversation.
Self-hosting still means configuring graph and vector storage backends yourself.
Is Cognee open source?
Yes. Cognee publishes an open-source SDK on GitHub under topoteretes/cognee, and you can run the full memory engine locally or on your own infrastructure for free. Cognee Cloud is a separate hosted option with usage-based pricing.
How is Cognee different from a vector database?
A vector database returns similar chunks. Cognee combines vectors with graph relationships, generated data models, and memory operations so agents retrieve connected context across sources rather than isolated snippets.
Can I run Cognee locally or self-host it?
Yes. Cognee installs with pip for local development and supports self-hosted deployments in Docker or private infrastructure. The product page also highlights air-gapped enterprise deployment with encryption at rest and in transit.
Which agent tools integrate with Cognee?
Cognee integrates with MCP clients including Claude Code and Codex, plus OpenClaw, Hermes, and other agent frameworks listed on the homepage. The same memory API is exposed through the SDK, HTTP, and MCP.
How does Cognee Cloud pricing work?
Cognee Cloud has a Free plan with 1 workspace and 1M tokens included at $0 per month. The Standard plan charges $2.50 per 1M tokens processed plus $5 per additional workspace per month. Enterprise pricing is available by contacting the team.
Which storage backends does Cognee support?
Cognee works with graph and vector backends such as Kuzu, NetworkX, Neo4j, FalkorDB, LanceDB, Qdrant, Milvus, and Redis, as listed on the FAQ page. Adapters also cover common document formats and external data sources.
Is Cognee GDPR compliant?
Cognee states on its product page that the platform is fully GDPR compliant, with data encrypted at rest and in transit. The site footer also displays heyData EU AI Act and GDPR compliance seals.