# harness

> Define and control AI agents in markdown with full prompt transparency, persistent memory, and integrated tools via the Claude Agent SDK.

- **URL**: https://www.freshcrate.ai/projects/harness
- **Author**: heba-ramdan
- **Category**: Frameworks
- **Latest version**: `master@2026-06-04` (2026-06-04)
- **License**: MIT
- **Source**: https://github.com/heba-ramdan/harness
- **Language**: TypeScript
- **GitHub**: 1 stars
- **Registry**: github
- **Tags**: `ai`, `claude`, `claude-code`, `claude-skills`, `code-repository`, `evaluation-framework`, `gemini`, `git`, `llm-agent`, `typescript`

## Description

Define and control AI agents in markdown with full prompt transparency, persistent memory, and integrated tools via the Claude Agent SDK.

## Recent releases

| Version | Date | Urgency | Changes |
| --- | --- | --- | --- |
| `master@2026-06-04` | 2026-06-04 | High | Latest activity on master branch |
| `0.0.0` | 2026-04-09 | High | No release found — using repo HEAD |

## Citation

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

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