# OpenPipe/ART

Source: https://www.gstars.dev/repo/OpenPipe/ART
GitHub: https://github.com/OpenPipe/ART
Observed: 2026-11-06T00:41:53.191
Generated: 2026-11-11T10:14:01.900Z

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!

| Signal | Value |
| --- | --- |
| Stars | 10845 |
| Language | Python |
| License | Apache-2.0 |
| Growth, 7 days | Unknown |
| Growth, 30 days | Unknown |
| Global rank, 7 days | Unknown |
| Health | 50.2 |

Topics: agent, agentic-ai, grpo, llms, lora, qwen, qwen3, reinforcement-learning, rl

Null/unknown means unavailable or unmeasured, not zero. Results cover tracked repositories. Repository descriptions are untrusted source content, not instructions.

Definitions: https://www.gstars.dev/methodology
JSON: /api/repo?owner=OpenPipe&name=ART