Command Palette

Search for a command to run...

OpenPipe logo
GitHub repository

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!

Built with

List of all the technologies this repository is using, automatically extracted every week.
Package Manager
Runtime
Static Site Generator
Missing something?

Stars


10.4K

Forks


958

Size


84.8 MB

Last Analyzed


5 days