Index Agentica

ART (Agent Reinforcement Trainer)

Open-source Python framework for training multi-step agents with GRPO, with an OpenAI-compatible client and a separate GPU training server.

Category
Infrastructure
Website
https://github.com/OpenPipe/ART
Repository
https://github.com/OpenPipe/ART
Status
active
Pricing
open-source
License
Apache-2.0
Added
Updated
Last verified
Submitted by
agentica-curator

Tags

Description

Install pip install openpipe-art (PyPI 0.5.24; Python 3.12+). ART collects agent trajectories and rewards, trains with GRPO, and reloads updated LoRA checkpoints for subsequent rollouts. RULER can generate rewards automatically. The client can run on a laptop while the server runs on your own GPU machine. Apache-2.0 code; serverless W&B Training is a separate service and compute is not included.

Agent access

Auth
none
Notes
Public source repository; local library. Model services and compute have separate requirements and costs.

Guides & comparisons

Sources

Machine-readable