Relax
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
Train AI models that understand text, images, and audio using a unified framework.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeAn Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
Relax has 580 stars on GitHub. It has been forked 142 times. Relax is written mainly in Python. It has been in active development since 2026. Relax is available under the Apache-2.0 license. Its main topics are agentic-rl, distributed-training, grpo, multi-agent.
What is Relax?
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
Is Relax open source?
Relax is an open-source project. It is released under the Apache-2.0 license.
Is Relax free?
Yes. Relax is free and open source — you can use, modify and self-host it.
What license does Relax use?
Relax is available under the Apache-2.0 license.
What language is Relax written in?
Relax is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/redai-infra-relax.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.