openenv/pr_749/en/llms.txt

# Openenv

## Docs

- [Release Notes](https://huggingface.co/docs/openenv/pr_749/release-notes.md)
- [Getting Started](https://huggingface.co/docs/openenv/pr_749/getting-started.md)
- [Contributing to OpenEnv](https://huggingface.co/docs/openenv/pr_749/contributing.md)
- [OpenEnv: Agentic Execution Environments](https://huggingface.co/docs/openenv/pr_749/index.md)
- [Environments](https://huggingface.co/docs/openenv/pr_749/environments.md)
- [Your First Environment](https://huggingface.co/docs/openenv/pr_749/guides/first-environment.md)
- [Reward Design](https://huggingface.co/docs/openenv/pr_749/guides/rewards.md)
- [Connecting to Servers](https://huggingface.co/docs/openenv/pr_749/guides/connecting.md)
- [RL Framework Integration](https://huggingface.co/docs/openenv/pr_749/guides/rl-integration.md)
- [MCP Environment Lifecycle](https://huggingface.co/docs/openenv/pr_749/guides/mcp-environment-lifecycle.md)
- [Custom Web UI](https://huggingface.co/docs/openenv/pr_749/guides/customizing-web-ui.md)
- [Simulation vs Production Mode](https://huggingface.co/docs/openenv/pr_749/guides/simulation-vs-production.md)
- [Auto-Discovery](https://huggingface.co/docs/openenv/pr_749/guides/auto-discovery.md)
- [Concepts](https://huggingface.co/docs/openenv/pr_749/guides/concepts.md)
- [Async vs Sync Usage](https://huggingface.co/docs/openenv/pr_749/guides/async-sync.md)
- [Auto Discovery](https://huggingface.co/docs/openenv/pr_749/reference/auto_discovery.md)
- [Core API](https://huggingface.co/docs/openenv/pr_749/reference/core.md)
- [CLI](https://huggingface.co/docs/openenv/pr_749/reference/cli.md)
- [API Reference](https://huggingface.co/docs/openenv/pr_749/reference/index.md)
- [Contributing to Hugging Face](https://huggingface.co/docs/openenv/pr_749/getting_started/contributing-envs.md)
- [Packaging & Deploying](https://huggingface.co/docs/openenv/pr_749/getting_started/environment-builder.md)
- [Julia](https://huggingface.co/docs/openenv/pr_749/environments/julia.md)
- [Kernrl](https://huggingface.co/docs/openenv/pr_749/environments/kernrl.md)
- [Coding](https://huggingface.co/docs/openenv/pr_749/environments/coding.md)
- [Finqa](https://huggingface.co/docs/openenv/pr_749/environments/finqa.md)
- [Snake](https://huggingface.co/docs/openenv/pr_749/environments/snake.md)
- [Repl](https://huggingface.co/docs/openenv/pr_749/environments/repl.md)
- [Openspiel](https://huggingface.co/docs/openenv/pr_749/environments/openspiel.md)
- [Terminus](https://huggingface.co/docs/openenv/pr_749/environments/terminus.md)
- [Chess](https://huggingface.co/docs/openenv/pr_749/environments/chess.md)
- [Git](https://huggingface.co/docs/openenv/pr_749/environments/git.md)
- [Reasoning Gym](https://huggingface.co/docs/openenv/pr_749/environments/reasoning_gym.md)
- [Maze](https://huggingface.co/docs/openenv/pr_749/environments/maze.md)
- [Textarena](https://huggingface.co/docs/openenv/pr_749/environments/textarena.md)
- [Tbench2](https://huggingface.co/docs/openenv/pr_749/environments/tbench2.md)
- [Jupyter](https://huggingface.co/docs/openenv/pr_749/environments/jupyter.md)
- [Agent World Model](https://huggingface.co/docs/openenv/pr_749/environments/agent_world_model.md)
- [Chat](https://huggingface.co/docs/openenv/pr_749/environments/chat.md)
- [Openapp](https://huggingface.co/docs/openenv/pr_749/environments/openapp.md)
- [Atari](https://huggingface.co/docs/openenv/pr_749/environments/atari.md)
- [Dipg](https://huggingface.co/docs/openenv/pr_749/environments/dipg.md)
- [Dm Control](https://huggingface.co/docs/openenv/pr_749/environments/dm_control.md)
- [Sumo](https://huggingface.co/docs/openenv/pr_749/environments/sumo.md)
- [Connect4](https://huggingface.co/docs/openenv/pr_749/environments/connect4.md)
- [Calendar](https://huggingface.co/docs/openenv/pr_749/environments/calendar.md)
- [Websearch](https://huggingface.co/docs/openenv/pr_749/environments/websearch.md)
- [Grid World](https://huggingface.co/docs/openenv/pr_749/environments/grid_world.md)
- [Echo](https://huggingface.co/docs/openenv/pr_749/environments/echo.md)
- [Opencode](https://huggingface.co/docs/openenv/pr_749/environments/opencode.md)
- [Coding Tools](https://huggingface.co/docs/openenv/pr_749/environments/coding_tools.md)
- [Finrl](https://huggingface.co/docs/openenv/pr_749/environments/finrl.md)
- [Wildfire](https://huggingface.co/docs/openenv/pr_749/environments/wildfire.md)
- [Carla](https://huggingface.co/docs/openenv/pr_749/environments/carla.md)
- [Browsergym](https://huggingface.co/docs/openenv/pr_749/environments/browsergym.md)
- [Unity](https://huggingface.co/docs/openenv/pr_749/environments/unity.md)
- [Rubrics: Composable Reward Computation](https://huggingface.co/docs/openenv/pr_749/tutorials/rubrics.md)
- [MCP Tools in OpenEnv Environments](https://huggingface.co/docs/openenv/pr_749/tutorials/mcp-environment.md)
- [Collecting rollouts with OpenEnv for supervised training](https://huggingface.co/docs/openenv/pr_749/tutorials/sft-warmup.md)
- [OpenEnv: Production RL Made Simple](https://huggingface.co/docs/openenv/pr_749/tutorials/openenv-tutorial.md)
- [BrowserGym Harness Rollouts](https://huggingface.co/docs/openenv/pr_749/tutorials/browsergym-harness.md)
- [End-to-end OpenEnv walkthrough: train a reasoning agent with GRPO](https://huggingface.co/docs/openenv/pr_749/tutorials/end-to-end-walkthrough.md)
- [OpenEnv Wordle with GRPO using TRL](https://huggingface.co/docs/openenv/pr_749/tutorials/wordle-grpo.md)
- [Tutorials](https://huggingface.co/docs/openenv/pr_749/tutorials/index.md)
- [Evaluating agents with Inspect AI](https://huggingface.co/docs/openenv/pr_749/tutorials/evaluation-inspect.md)
- [RL Training with OpenEnv: 2048 Game](https://huggingface.co/docs/openenv/pr_749/tutorials/rl-training-2048.md)