# huggingface/OpenEnv

An interface library for RL post training with environments.

Repository: https://github.com/huggingface/OpenEnv
Canonical: https://ross.abutalabs.com/products/openenv
Homepage: https://huggingface.co/docs/openenv/index
Language: Python
License: BSD-3-Clause
License Family: permissive
Last push: 2026-08-26T17:49:45+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 91, longevity 24
- inputs: {"age_days": 336, "days_push": 7, "days_rel": 61, "gap_med": 25.5, "n_releases_24m": 7}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2521, forks 428 (observed 2026-08-28T04:06:58.284509+00:00)

## What it is
OpenEnv is a Hugging Face framework for creating, deploying, and consuming isolated execution environments used in agentic reinforcement learning post-training of LLMs. It provides Gymnasium-style step/reset/state APIs, container-based HTTP environment servers, auto-discovery clients, a CLI for scaffolding and deployment, and composable rubrics for reward design.

## Use cases
- create custom environments for RL post-training of LLMs
- train agents with GRPO in gym-style environments
- deploy sandboxed execution environments for agentic RL
- integrate TRL or torchforge trainers with external environments
- package an RL environment as a Docker container and serve it over HTTP
- find prebuilt environments for coding, games, or web-browsing tasks
- design reward functions and rubrics for RL training

## When to choose
- You are doing RL post-training (e.g., GRPO) of LLMs and need a standardized environment interface
- You want Gymnasium-style step/reset APIs that plug into TRL, torchforge, or SkyRL
- You need secure, containerized, HTTP-served environments for distributed or remote training
- You want to publish environments to Hugging Face Spaces and auto-discover them via AutoEnv/AutoAction

## When to avoid
- You run classic single-machine RL research (Atari, MuJoCo) where plain Gymnasium already suffices
- You need an inference-time agent framework rather than training environments
- Your stack is not Python-centric
- You require a mature 1.0 release; the project is still at v0.4.x with some docs in progress

## Facets
- artifact type: framework
- maturity: active
- function: reinforcement-learning, agent-framework, http-server, mcp, cli
- domain: reinforcement-learning, large-language-models, machine-learning, developer-tools
- platform: python, cloud, self-hosted
- tags: gymnasium, rl-environments, post-training, grpo, reward-design, rubrics, sandboxed-execution, environment-server, auto-discovery, fastapi, hugging-face, trl-integration, containerized-environments, ai-agents, docker

## Member repositories
- huggingface/OpenEnv (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:58.284509+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:25:55.832240+00:00, confidence not recorded.
  - readme: https://github.com/huggingface/OpenEnv (fetched 2026-08-28T04:06:58.284509+00:00, sha 55ffcd768196)
  - homepage: https://huggingface.co/docs/openenv/index (fetched 2026-08-29T10:08:18.225634+00:00, sha ba4204fa67d4)
  - site_page: https://huggingface.co/docs (fetched 2026-08-29T10:08:18.235178+00:00, sha bdec26667b98)
  - site_page: https://huggingface.co/docs/openenv/getting-started (fetched 2026-08-29T10:08:18.239257+00:00, sha 72c83d584df5)
  - site_page: https://huggingface.co/docs/openenv/guides/first-environment (fetched 2026-08-29T10:08:18.240979+00:00, sha af62c15a1f8e)
  - site_page: https://huggingface.co/docs/openenv/getting_started/environment-builder (fetched 2026-08-29T10:08:18.242516+00:00, sha ed93cea32a61)
  - site_page: https://huggingface.co/docs/openenv/guides/auto-discovery (fetched 2026-08-29T10:08:18.244505+00:00, sha 64dc76d7c90c)
  - site_page: https://huggingface.co/docs/openenv/guides/rl-integration (fetched 2026-08-29T10:08:18.246518+00:00, sha d1d1720a5b95)
  - site_page: https://huggingface.co/docs/openenv/guides/rewards (fetched 2026-08-29T10:08:18.248199+00:00, sha 2dc8d99302ba)
  - site_page: https://huggingface.co/pricing (fetched 2026-08-29T10:08:18.237316+00:00, sha de6b7a178be5)
- Data as of 2026-08-30T08:39:29.467469+00:00.