Optimize AI agents without changing their code by using various training algorithms.
From the README
- Trainer: Runs verl and vLLM, builds training samples, and updates the policy.
- API Gateway: Proxies model requests and captures training data.
- Rollout Controller: Runs agents locally or as Kubernetes Jobs.
Excerpts from the project README on GitHub. Copyright and licensing remain with the respective authors.
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 anytimeThe absolute trainer to light up AI agents.
agent-lightning has 17.9k stars on GitHub. It has been forked 1.6k times. agent-lightning is written mainly in Python. It has been in active development since 2025. agent-lightning is available under the MIT license. Its main topics are agent, agentic-ai, llm, mlops.
What is agent-lightning?
The absolute trainer to light up AI agents.
Is agent-lightning open source?
agent-lightning is an open-source project. It is released under the MIT license.
Is agent-lightning free?
Yes. agent-lightning is free and open source — you can use, modify and self-host it.
What license does agent-lightning use?
agent-lightning is available under the MIT license.
What language is agent-lightning written in?
agent-lightning is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/microsoft-agent-lightning.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.