What is ART (Agent RL Trainer)?

ART (Agent RL Trainer) is an open-source AI agent in the Framework category. Train and optimize AI agents with reinforcement learning from agent trajectories.

Who maintains ART (Agent RL Trainer) and how active is it?

ART (Agent RL Trainer) is maintained by OpenPipe on GitHub (9,000 stars at indexing time). LLM Explorer tracks its star count, fork count, last commit, and license over time.

Is ART (Agent RL Trainer) open source and what is its license?

ART (Agent RL Trainer) is published under the Apache-2.0 license. Check the linked repository on this page for current terms before integrating.

LLM EXPLORER 61,755 MODELS INDEXED

ART (Agent RL Trainer)

Name: ART (Agent RL Trainer)
Author: OpenPipe

» AI Agents » Framework » ART (Agent RL Trainer) URL Share on

Repository 9,000 774

Train and optimize AI agents with reinforcement learning from agent trajectories

reinforcement-learning training fine-tuning agent-optimization

TypeFramework

HostingSelf-Hosted

MaturityBeta

Status Maintained

Website Repository

Key Features

Single Agent Self-Hosted

ART (Agent RL Trainer) Details

Organization	OpenPipe
Organization Type	Company
Category	Framework
Subcategory	Training
Deployment	Self-Hosted
Primary Language	Python
License	Apache-2.0
Commercial Use	Permissive
GitHub Stars	9,000
GitHub Forks	774
Maturity	Beta
Pricing Model	Free
Self-Hosted Free	Yes
Cost Model	free + LLM costs
Community Size	Large
Community Activity	Active
Sentiment	Positive
GPU Required	No
Research Date	2026-03-24

Back to Agent Directory