OpenEnv: Agentic Execution Environments

Team

community

https://github.com/meta-pytorch/OpenEnv

meta-pytorch

Activity Feed

Follow

446

OpenEnv: Agentic Execution Environments

\n\n

An e2e framework for creating, deploying and using isolated execution environments for agentic RL training, built using Gymnasium style simple APIs. A community driven collection of OpenEnv-spec Environments composed of a Hub and a Standardized spec to ensure environment compatibility.

Quick Start

You can install Hugging Face spaces for client code:

pip install git+https://huggingface.co/spaces/openenv/echo_env\n

Then use the environment hosted on spaces:

import asyncio\nfrom echo_env import EchoAction, EchoEnv\n\nasync def main():\n    # Connect to a running Space (async context manager)\n    async with EchoEnv(base_url=\"https://openenv-echo-env.hf.space\") as client:\n        # Reset the environment\n        result = await client.reset()\n        print(result.observation.echoed_message)  # \"Echo environment ready!\"\n\n        # Send messages\n        result = await client.step(EchoAction(message=\"Hello, World!\"))\n        print(result.observation.echoed_message)  # \"Hello, World!\"\n        print(result.reward)  # 1.3 (based on message length)\n\nasyncio.run(main())\n

To pull the environments locally from Spaces as docker containers, you can do this:

import asyncio\nfrom echo_env import EchoEnv\n\nasync def main():\n    # Pulls from Hugging Face and starts a container\n    client = await EchoEnv.from_env(\"openenv/echo_env\")\n    async with client:\n        result = await client.reset()\n        print(result.observation)\n\nasyncio.run(main())\n

Hugging Face x Meta-PyTorch

Hugging Face, Meta-PyTorch and many other supporters are committed to democratizing RL post training with environmnets.

AI & ML interests

None defined yet.

Recent Activity

qgallouedec  updated a Space 1 day ago

openenv/wordle

burtenshaw  updated a Space 4 days ago

openenv/grid_world_env-v2-1-0

burtenshaw  published a Space 4 days ago

openenv/grid_world_env-v2-1-0

View all activity

Team members 11

Organization Card

Community About org cards

OpenEnv: Agentic Execution Environments

An e2e framework for creating, deploying and using isolated execution environments for agentic RL training, built using Gymnasium style simple APIs. A community driven collection of OpenEnv-spec Environments composed of a Hub and a Standardized spec to ensure environment compatibility.

Join the Hackathon!

Additionally, we’re thrilled to announce a new AgentBeats custom track: the OpenEnv Challenge: SOTA Environments to Drive General Intelligence, sponsored by the PyTorch team at Meta, Hugging Face, and Unsloth. Participants will compete to develop innovative, open-source RL environments that push the frontiers of agent learning, with a prize pool of $10K in Hugging Face credits, and the chance to be published on the PyTorch blog

Sign up here

Quick Start

You can install Hugging Face spaces for client code:

pip install git+https://huggingface.co/spaces/openenv/echo_env

Then use the environment hosted on spaces:

import asyncio
from echo_env import EchoAction, EchoEnv

async def main():
    # Connect to a running Space (async context manager)
    async with EchoEnv(base_url="https://openenv-echo-env.hf.space") as client:
        # Reset the environment
        result = await client.reset()
        print(result.observation.echoed_message)  # "Echo environment ready!"

        # Send messages
        result = await client.step(EchoAction(message="Hello, World!"))
        print(result.observation.echoed_message)  # "Hello, World!"
        print(result.reward)  # 1.3 (based on message length)

asyncio.run(main())

To pull the environments locally from Spaces as docker containers, you can do this:

import asyncio
from echo_env import EchoEnv

async def main():
    # Pulls from Hugging Face and starts a container
    client = await EchoEnv.from_env("openenv/echo_env")
    async with client:
        result = await client.reset()
        print(result.observation)

asyncio.run(main())

Hugging Face x Meta-PyTorch

Hugging Face, Meta-PyTorch and many other supporters are committed to democratizing RL post training with environmnets.

Collections 6

OpenEnv Environment Hub v2.1.0

OpenEnv spaces for release v2.1.0

• Running

  BrowserGym Environment Server

  🌐

  Control a simulated environment with natural‑language actions

• Running

  RL

  Chat Environment Server

  💬

• Running

  RL

  chess_env Environment

  🚀

  Control an interactive environment and view real-time state updates

• Sleeping

  RL

  Coding Environment Server

  💻

Coding Agents

• Runtime error

  RL

  12

  Coding Environment Server

  💻

  12

• Sleeping

  RL

  TB2 Environment Server

  🧪

  Control and monitor AI agent environments through web interface

• Sleeping

  Julia_env Environment Server

  🐳

• 

  Infatoshi/kernrl-training

  Reinforcement Learning • Updated about 1 month ago

OpenEnv Environment Hub v2.1.0

OpenEnv spaces for release v2.1.0

• Running

  BrowserGym Environment Server

  🌐

  Control a simulated environment with natural‑language actions

• Running

  RL

  Chat Environment Server

  💬

• Running

  RL

  chess_env Environment

  🚀

  Control an interactive environment and view real-time state updates

• Sleeping

  RL

  Coding Environment Server

  💻

Coding Agents

• Runtime error

  RL

  12

  Coding Environment Server

  💻

  12

• Sleeping

  RL

  TB2 Environment Server

  🧪

  Control and monitor AI agent environments through web interface

• Sleeping

  Julia_env Environment Server

  🐳

• 

  Infatoshi/kernrl-training

  Reinforcement Learning • Updated about 1 month ago

View 6 collections

spaces 35

Sort:  Recently updated

Running

RL

Wordle

🎮

Interact with a custom environment via text actions

Runtime error

RL

Grid World Env

🌍

Running

RL

finrl_env Environment

🚀

Running

RL

OpenApp Environment Server

🌐

Running

RL

git_env Environment

🚀

Running

RL

chess_env Environment

🚀

Control an interactive environment and view real-time state updates

View 35 Spaces

models 0

None public yet

datasets 0

None public yet