NVIDIA-NeMo / Gym
Evaluate and improve models and agents using environments
Why this job: topics: evaluation, benchmarks
What it does
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.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit today
- Stars
- 1,326
- +13 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.7.0
- Released 29 days ago
- Built with
- Python
- 88% of the code
Is it looked after?
- Contributors
- 34
- Last 90 days
- Issues
- 55% closed
- 627 still open
- Pull requests
- 2,549 merged
- 863 waiting
- Releases
- 10
- 10 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| hud-evals / hud-python | 325 | today | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 88%
- MDX 10%
- Shell 1%
- JavaScript <1%
Topics
- reinforcement-learning
- reinforcement-learning-environments
- rl-environment
- rl-training
- gym
- agents
- benchmarks
- environments
- evaluation
- llm
Project record
- JobEvals and observability
- StatusFeatured
- Commits2,277
- Forks456
- Watching8
- Stars in 28 days+96
- CreatedAug 25, 2025
- First seen by usNov 7, 2026
- CheckedNov 10, 2026