huggingface/OpenEnv

An interface library for RL post training with environments.

About the project

OpenEnv is a framework for creating, deploying, and using isolated execution environments through simple APIs modeled on Gymnasium. It is intended for researchers and developers training agents with reinforcement learning, as well as creators who need secure environments that can be deployed and accessed through familiar protocols. The catalogue add-ons provide agent integrations and workflows for using OpenEnv.

Latest release v0.4.1 · 3 Jul 2026

These files are huggingface/OpenEnv's own configuration. They tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.

2,544Stars on the repository
32Files it configures its agents with
3,744Tokens loaded in every session
3Agents configured

Instructions

Settings

Hooks

Skills

Agents