# Harness Library

> Open directory of reusable AI agent harnesses, with focused distributions and clear setup instructions.

An agent harness is the surrounding setup that lets an AI model act on a task. It can include instructions, skills, tools, environment mappings, checks and workflows. Harness Library focuses on reusable, task-specific setups: from a small skill folder to an MCP workflow or a larger harness package.

New community submissions are welcome. Harneloop is optional. Review labels describe specific evidence; they do not guarantee every model/platform.

## Directory
- [Catalog](https://kaelux-labs.github.io/harness-library/index.md): Overview and available harnesses.
- [About the library](https://kaelux-labs.github.io/harness-library/about/index.md): Definitions, maintainer, review scope and FAQ.
- [Submit a harness](https://kaelux-labs.github.io/harness-library/submit/index.md): Short issue-first submission process.

## Harness installation guides
- [Smooth Motion Graphics](https://kaelux-labs.github.io/harness-library/harnesses/smooth-motion-graphics/index.md): A compact skill for calm, clear brand animations.
- [ViperMesh for Blender](https://kaelux-labs.github.io/harness-library/harnesses/vipermesh-blender/index.md): A local Blender MCP workflow for building and checking 3D scenes.

## Data
- [Machine-readable catalog](https://kaelux-labs.github.io/harness-library/catalog.json): Reviewed listings with source, distribution, install steps, manual setup, license and evidence.
- [Full text](https://kaelux-labs.github.io/harness-library/llms-full.txt): Combined public guide and installation text.