What it does

All text below is quoted directly from the project README.

Cognee is a free open-source AI memory platform that gives AI agents persistent long-term memory across sessions. Turn documents, code, and conversations into a self-hosted knowledge graph your agents can search and reuse.

Runs locally for free — no API key required. We rely on free small models that use your CPU.

When to use Cognee:

• Build a Company Brain. Bring documentation, conversations, tickets, code, and agent work into shared memory. Help your team and agents connect a decision to the discussion and implementation behind it.
• Give agents memory across runs. Retain project context, past decisions, fixes, and learned rules. Distill useful session lessons into durable knowledge that another session can retrieve.
• Ground agents in your domain. Structure memory around the entities and relationships your application needs, with custom data models and ontologies.

How Cognee works:

Cognee builds connected memory from different sources. Text becomes entities, relationships, and searchable chunks; code becomes a graph of symbols and dependencies. Session distillation curates accepted lessons into permanent memory.

• remember: Store content or code in permanent memory, or in a session when a session ID is supplied.
• recall: Retrieve context and answers, using automatic routing or a chosen search strategy.
• improve: Enrich memory, apply feedback, and bridge session knowledge into the graph.
• forget: Remove a specific item or dataset.

Text ingestion, retrieval, and session storage work without an LLM. LLM-dependent improvement stages skip automatically.

Repository

https://github.com/topoteretes/cognee

Repository stats

Main contributor