A
ART
OpenPipe/ART
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!
★10.6kstars
Python
Apache-2.0
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?A agent/agentic-ai tool in the Agents category, built with Python, open-source
Who made it?Maintained by OpenPipe team, 10.6K⭐ on GitHub, #187 out of 2166 in Agents
Why does it exist?With the growing demand for agent and agentic-ai in Agents, OpenPipe created ART as a streamlined solution.
What can it do?Key use cases: grpo, llms, lora
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/OpenPipe/ART | 官网 https://art.openpipe.ai
🔗 github.com/OpenPipe/ART | 官网 https://art.openpipe.ai
Topics
agentagentic-aigrpollmsloraqwenqwen3reinforcement-learningrl