Home Projects Raven
Raven
Python

Raven

The Harness of Harnesses: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

by EverMind-AI · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
aiai-agentsanthropicApache-2.0Python
View on GitHub
In plain words

Use Raven to create and improve AI agents that learn from their experiences and adapt over time.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
Raven — GitHub preview card
📈 Star history
4k2k
2026-07-202026-08-31
📈 Track Raven

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

The Harness of Harnesses: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

Raven has 3.7k stars on GitHub. It has been forked 73 times. Raven is written mainly in Python. It has been in active development since 2026. Raven is available under the Apache-2.0 license. Its main topics are ai, ai-agents, anthropic, chatgpt.

Frequently asked questions

What is Raven?

The Harness of Harnesses: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

Is Raven open source?

Raven is an open-source project. It is released under the Apache-2.0 license.

Is Raven free?

Yes. Raven is free and open source — you can use, modify and self-host it.

What license does Raven use?

Raven is available under the Apache-2.0 license.

What language is Raven written in?

Raven is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — Raven

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=evermind-ai-raven)](https://olud.ai/project/evermind-ai-raven.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.