← Agent Marketplace
Open-source project

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!

9,968 starsSelf-host

Skills

An open-source project — explore the code and self-host it from GitHub.