AI Agents
langmem
LangMem: long-term memory primitives for LangGraph agents that learn and adapt from conversations.
★ 1.7k starsMIT
View guide →// agents · topoteretes/cognee
cognee
cognee is an open-source ai agents project by topoteretes (topoteretes/cognee on GitHub). It has 31,591 GitHub stars and 3,246 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 8 October 2026.
Open-source AI memory that gives agents persistent long-term recall.
★ 31.6k stars⑂ 3.2k forksApache-2.0updated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- topoteretes/cognee
- GitHub stars
- 31,591
- Forks
- 3,246
- License
- Apache-2.0
- Last updated on GitHub
- 8 October 2026
- Category
- AI Agents
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Define the job
Write down the task or workflow you want the agent to handle.
- Get the code
Clone the repository and read the README's prerequisites.
- Set up your environment
Install dependencies and configure keys or endpoints.
- Try the quickstart
Run the sample script and check the output against the docs.
// features
Why people love it
Knowledge-graph memory
Facts stored as connected graphs, not flat text.
Long-term persistence
Memory that survives across sessions.
Small-model friendly
Designed to work well without giant models.
Context engineering
Focus on how memory is structured for retrieval.
Apache-2.0
Permissive open-source license.
Active community
Large star count and steady pushes.
Advertisement
// run it
Run it yourself
- Step 1 - Clone the repo
Download the source and move into the project folder.
git clone https://github.com/topoteretes/cognee.git cd cognee - Step 2 - Install dependencies
Create a virtual environment and install the requirements.
python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt - Step 3 - Run an example
Treat these as starting points - the README documents the exact commands.
python examples/quickstart.py
// use cases
What you can build
- Give a research agent a growing knowledge graph.
- Build agents that recall relationships between facts.
- Add cheap long-term memory using small models.
- Prototype cognitive-architecture memory designs.
Advertisement
// faq
Questions, answered
Who is behind cognee?
The project lives at topoteretes/cognee and has attracted 3246 forks. Browse its commit history and contributor list for a sense of maintenance pace.
Is cognee free to use?
Yes - it is Apache-2.0 licensed, so it is free for commercial use with attribution.
Do I need a paid API to use it?
It depends on your setup - self-hosted storage can be free, while hosted tiers or embedding APIs may cost money. Check the README for options.
How does it compare to mem0?
mem0 is a drop-in memory API; cognee is a knowledge-graph memory platform with a cognitive-architecture angle. If graph-structured recall appeals to you, start with cognee.
Where should I start?
The README and the official docs site are the fastest path: run the quickstart example first, then adapt it to your use case.
// keep exploring
Similar tools
AI Agents
agent-memory
Long-term memory runtime for AI agents — plain Markdown as truth, local ranked retrieval, no API key
★ 2.6k starsMIT
View guide →AI Agents
magic-context
Self-managing, unbounded context and long-term memory for coding agents: one session, for life.
★ 2.3k starsMIT
View guide →AI Agents
MemoryOS
A memory operating system for long-term, personalized AI agents.
★ 1.6k starsApache-2.0
View guide →AI Agents
memobase
User-profile-based long-term memory for AI chatbot applications
★ 2.9k starsApache-2.0
View guide →AI Agents
LongMemory
LongMemory: local-first memory for AI agents with temporal truth, provenance, and hybrid recall
★ 4.5k starsApache-2.0
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if cognee is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to cognee — keep exploring the shelf either side of it.
- agentscope★ 32.9k
Build and run agents you can see, understand and trust — framework plus a visual agent service
- graphiti★ 31.5k
Real-time knowledge graphs that give agents a memory with structure.
- github-mcp-server★ 33.4k
GitHub's official MCP server — let AI tools work with repos, issues and pull requests
- supermemory★ 31.2k
The memory API that gives AI apps instant, lasting context.
- openclaude★ 33.7k
A Claude Code-style coding agent that runs anywhere and works with almost any model provider
- nanoclaw★ 30.9k
A lightweight, container-isolated personal AI agent for WhatsApp, Telegram, Slack and more
Get cognee
Free and open — grab the source, star the repo, and start creating.