> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/gym/v0.5.1/contribute/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/gym/_mcp/server.

# Overview

Welcome! We are excited to have you contribute to NeMo Gym. Whether you are adding new training environments, integrating RL frameworks, improving documentation, or fixing bugs, your contributions help advance RL training.

---

## Ways to Contribute

#### Add Environments

New environments expand Gym's training capabilities.

* Novel training environments (coding, reasoning, tool use, games, and so on)
* Benchmark integrations (such as SWE-Bench and Tau Bench)

→ Refer to [contribute-environments](/contribute/environments) for guidance.

#### Integrate RL Frameworks

Have a preferred training framework? Help integrate it with NeMo Gym.

→ Refer to [training-framework-integration](/contribute/rl-framework-integration) for integration guides.

#### Improve Documentation

* New tutorials and advanced guides
* Code examples and best practices
* API documentation improvements

#### Use Agent Skills

NeMo Gym ships vetted agent skills that accelerate common development workflows with AI coding assistants.

→ Refer to [Agent Skills](/contribute/agent-skills) for the available skills and how to use them.

#### Report Bugs & Fix Issues

* Found a bug? [Open an issue](https://github.com/NVIDIA-NeMo/Gym/issues/new?template=bug.md) with reproduction steps.
* Want to fix one? Check [open issues](https://github.com/NVIDIA-NeMo/Gym/issues) for bugs to tackle.

#### Features & Enhancements

Have an idea for a new feature or improvement? [Open an issue](https://github.com/NVIDIA-NeMo/Gym/issues/new?template=feature.md) to start a discussion!

---

## Before You Start

All contributions require signed commits and DCO sign-off. Refer to [development-setup](/contribute/development-setup) for environment setup, CI/CD requirements, and commit signing instructions.

**Not sure where to start?** Check our [open issues](https://github.com/NVIDIA-NeMo/Gym/issues) or create a new issue to discuss your idea.

## Docs

- [Development Setup](https://docs.nvidia.com/nemo/gym/v0.5.1/contribute/development-setup.md): 
- [Environments](https://docs.nvidia.com/nemo/gym/v0.5.1/contribute/environments.md): 
- [Add a benchmark](https://docs.nvidia.com/nemo/gym/v0.5.1/contribute/environments/adding-a-benchmark.md): 
- [New Environment](https://docs.nvidia.com/nemo/gym/v0.5.1/contribute/environments/new-environment.md): 
- [Integrate RL Frameworks](https://docs.nvidia.com/nemo/gym/v0.5.1/contribute/rl-framework-integration.md): 
- [Generation Backend](https://docs.nvidia.com/nemo/gym/v0.5.1/contribute/rl-framework-integration/generation-backend-and-openai-compatible-http-server.md): 
- [Integration Footprint](https://docs.nvidia.com/nemo/gym/v0.5.1/contribute/rl-framework-integration/gym-integration-footprint-and-form-factor.md): 
- [On-Policy Corrections](https://docs.nvidia.com/nemo/gym/v0.5.1/contribute/rl-framework-integration/openai-compatible-http-server-on-policy-correction.md): 
- [Success Criteria](https://docs.nvidia.com/nemo/gym/v0.5.1/contribute/rl-framework-integration/gym-rl-framework-integration-success-criteria.md): 
- [Agent Skills](https://docs.nvidia.com/nemo/gym/v0.5.1/contribute/agent-skills.md): Vetted workflows for AI coding assistants bundled with NeMo Gym.