hud-evals / hud-python
RL environments + evals for AI agents. Define once, train anything.
Why this job: says: evals; topics: evals
What it does
HUD is a platform for building RL environments for AI agents, across coding, browser, computer-use, and robotics. Define an environment, write tasks, and run them as evals and training across any model, at any scale.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 3 days ago
- Stars
- 324
- +2 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.6.22
- Released 6 days ago
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- 11
- Last 90 days
- Issues
- 92% closed
- 2 still open
- Pull requests
- 559 merged
- 6 waiting
- Releases
- 174
- 30+ in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| JudgmentLabs / judgeval | 1,073 | 13 days ago | Apache-2.0 | No downloads |
| NVIDIA-NeMo / Gym | 1,325 | yesterday | Apache-2.0 | No downloads |
| GitHamza0206 / simba | 1,547 | 4 months ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 99%
- Shell 1%
- Dockerfile <1%
Topics
- grpo
- llm
- qwen3
- reinforcement-learning
- reinforcement-learning-environments
- rl
- agents
- evals
- qwen
Project record
- JobEvals and observability
- StatusListed
- Commits3,597
- Forks91
- Watching2
- Stars in 28 days+13
- CreatedMar 2, 2025
- First seen by usNov 7, 2026
- CheckedNov 9, 2026