claw-eval / claw-eval
Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.
Why this job: matched by what the repo talks about: evaluation, eval, llm, evaluat
What it does
Clones and views are accumulated daily from the GitHub Traffic API since 2026-07-22. Dataset downloads are the sum of all-time HuggingFace and ModelScope counts. Raw daily data lives in traffic/traffic.json.
Get started
pip install uv
uv venv --python 3.11
source .venv/bin/activate - Maintenance
- Active
- Last commit 3 months ago
- Stars
- 920
- +26 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- 0
- Last 90 days
- Issues
- 87% closed
- 6 still open
- Pull requests
- 3 merged
- 5 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| suyoumo / ClawProBench | 830 | 2 months ago | Apache-2.0 | No downloads |
| agentscope-ai / PawBench | 127 | 3 months ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 99%
- HTML <1%
- Shell <1%
Topics
- agent
- harness
- llm
- openclaw
Project record
- JobEvals and observability
- StatusListed
- Commits52
- Forks98
- Watching6
- Stars in 28 days+148
- CreatedMar 11, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026