🌱 Open Source
Back to Open Source

🐙 GitHub Detail

A

OpenPipe/ART

By OpenPipe

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

GitHub Python Apache License 2.0 Updated 09 Jun 2026

Live Snapshot

Stars

9,958

🍴

Forks

891

📄

License

Apache License 2.0

🧩

Type

Python

📘

About this open-source project

Live information fetched from GitHub.

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

🌿

Default Branch

main

🐞

Open Issues

124

👀

Watchers

9,958