Run This Ai
EN DE

Cognee

Open-source AI memory platform for agents with persistent long-term memory across sessions

★ 27,592 GitHub Apache-2.0 ai-memoryknowledge-graphagentsllmragpythonself-hosted RAG & Knowledge

Overview

Cognee is an open-source AI memory platform that gives your AI agents persistent long-term memory across sessions. Built on a self-hosted knowledge graph engine, Cognee stores, retrieves, and manages agent memories in a structured way — enabling agents to remember past conversations, decisions, and context. With 27K+ GitHub stars, it is the leading open-source solution for AI agent memory. The platform features a flexible memory graph that supports multiple memory types (episodic, semantic, procedural), a REST API for easy integration, and a Python SDK. Cognee runs entirely on your infrastructure, ensuring data privacy and control. It integrates with any LLM provider and agent framework, making it ideal for building AI agents that learn and improve over time. Key capabilities include automatic memory summarization, graph-based retrieval for relevant context, configurable memory retention policies, and multi-user memory isolation. Cognee is Apache-2.0 licensed and deploys via Docker with a single command.

Requirements

Min vCPU
2
Min RAM
4096 MB
Min Disk
10 GB
Rec vCPU
4
Rec RAM
8192 MB
Rec Disk
20 GB

Recommended VPS

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 4

4 vCPU · 16384 MB · 200 GB

$11.99
View plan

Hostinger · KVM 8

8 vCPU · 32256 MB · 400 GB

$20.00
View plan

Affiliate disclosure

Docker Compose

# Generated by Run This Ai — docker-compose.yml
services:
  cognee:
    image: cognee/cognee:latest
    restart: unless-stopped
    ports:
      - 8080:8080
    volumes:
      - ./data/cognee:/data

Best VPS for Cognee →

Related tools

Guides & articles