> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/gym/llms.txt.
> For full documentation content, see https://docs.nvidia.com/nemo/gym/llms-full.txt.

# NeMo Gym

> NeMo Gym is a library for evaluating and improving models and agents using environments.

# NeMo Gym

NeMo Gym is a library for evaluating and improving models and agents using environments. NeMo Gym provides infrastructure to develop environments, scalably run evaluation and training, and a collection of popular benchmarks and training environments.

## When to Use NeMo Gym

* You need to **evaluate models or agents** in stateful environments (for example, code execution, tool calling, sandboxes).
* You want **reproducible evaluation** across teams using shared environments and verifiers.
* You need to use environments **at scale** — multiple repeats per task, or thousands of concurrent requests for training.
* You want to **seamlessly transition** between evaluation, agent optimization, and training.

If you are scoring model outputs with a stateless check and do not need scale or training, a script is probably sufficient.

## What NeMo Gym Provides

* Modular, extensible interfaces for agents, environments, tasks, and verifiers
* Environment hub of popular benchmarks and training environments
* Use your own agents or choose from built-in harnesses
* Scale to thousands of concurrent environments
* Train with the RL framework of your choice
* Battle-tested in production Nemotron training

![NeMo Gym Product Overview](file:d6041a52-d3bd-410e-8f2e-49a4646f7fad)

## Integrations

NeMo Gym integrates with the broader agentic ecosystem:

* **Environment libraries**: Seamlessly combine environments and benchmarks from other libraries alongside NeMo Gym environments.
* **Training framework libraries**: Use environments for SFT and RL training.
* **Agent harnesses**: Popular agent harnesses for evaluation and training available out of the box.
* **Agent framework libraries**: Use your custom agent built with agent frameworks in NeMo Gym environments.
* **Sandboxes**: Isolate agent runtime execution.