Verified project record

topoteretes/cognee

A self-hosted memory platform for AI agents that ingests data in any format to build a knowledge graph, enabling persistent long-term memory and contextual reasoning. It exposes memory operations through four API actions and can optionally run the entire memory layer on a single Postgres instance.

Project overview

Project type: MCP · AI Agent · RAG
Use cases: Knowledge Q&A · Automation
Deployment: Refer to project documentation
License: Apache-2.0

Best for

Developers and AI engineers who need a self-hosted knowledge graph to provide AI agents with persistent long-term memory.
Enterprise teams requiring a unified memory layer that can operate on a single Postgres instance.

Key capabilities

Gives AI agents persistent long-term memory across sessions by continuously building a self-hosted knowledge graph.
Combines vector embeddings, graph reasoning, and cognitive-science-grounded ontology generation to make documents searchable by meaning and connected by relationships.
Ingests data in any format to unify data from various sources in one place.
Provides four API operations to manage agent memory: remember, recall, forget, and improve.
Allows running the entire memory layer including graph relationships, embeddings, sessions, and metadata on a single Postgres instance.

Limitations and risks

Requires an external LLM API key to function.
Depends on external Large Language Models for processing.

Getting started

Install via a single pip command, configure the LLM API key, and execute memory operations via the CLI or as a library.

Evidence and sources

GitHub project description: Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
README: Cognee is an open-source AI memory platform for AI Agents. Ingest data in any format, and Cognee continuously builds a self-hosted knowledge graph that gives your agents persisten…
README: we beat the previous state of the art at the 100K-token setting and matched it at 10M tokens.
Release: v1.3.0 — Smarter Search & Dataset Indexing
README: Easily Build Company Brain - unify data from various sources in one place and enable Agents with your domain knowledge

Reviewed at: 2026-07-17T10:15:07Z