What it does
rLLM is a framework for training language-model agents with reinforcement learning, where the AI tries tasks, gets scored and learns from the results.
It works with many existing agent tools, including Claude Code and Codex, runs them in sandboxes, and includes more than 60 tests in areas like maths, coding and search.
Its makers say it has been used to train several open models and by academic and industry research teams.
Who it's for
AI researchers and engineers training their own agent models.
Can I use it without coding?
Developers only. It's a Python framework for machine learning engineers. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Server, Linux
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe