# claw-eval

> Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

- **URL**: https://www.freshcrate.ai/projects/claw-eval
- **Author**: claw-eval
- **Category**: Testing
- **Latest version**: `main@2026-05-17` (2026-05-17)
- **License**: Unknown
- **Source**: https://github.com/claw-eval/claw-eval
- **Homepage**: https://claw-eval.github.io
- **Language**: Python
- **GitHub**: 465 stars, 37 forks
- **Registry**: github
- **Tags**: `agent`, `harness`, `llm`, `openclaw`, `python`

## Description

Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `main@2026-05-17` | 2026-05-17 | High | Latest activity on main branch |
| `0.0.0` | 2026-04-11 | High | No release found — using repo HEAD |

## Citation

- HTML: https://www.freshcrate.ai/projects/claw-eval
- Markdown: https://www.freshcrate.ai/projects/claw-eval.md
- Dependencies JSON: https://www.freshcrate.ai/api/projects/claw-eval/deps

_Generated by freshcrate.ai. Indexes github releases for AI-agent ecosystem packages._