kirillbrsnkv/give-claude-eyes

README preview

# Give Claude Eyes

### Multimodal video & image understanding via Qwen Omni

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
[![Claude Code](https://img.shields.io/badge/Claude-Code%20%2F%20Cowork-blueviolet)](https://claude.ai)
[![Python 3.9+](https://img.shields.io/badge/Python-3.9%2B-blue.svg)](https://www.python.org/)

Claude can't natively watch video. This plugin fixes that -- it bridges Claude with [Qwen Omni](https://help.aliyun.com/zh/model-studio/developer-reference/qwen-omni), a natively multimodal model that actually sees motion, not just individual frames. When you mention a video or ask for visual analysis, Claude calls Qwen under the hood and works with the result. For you as the user, it just feels like Claude can see.

```
You --> Claude --> Qwen Omni API --> Claude --> You
         "analyze this video"    (watches it)   "here's what I saw"
```

## Quick start

### Install

**Claude Code:**

View full repository on GitHub →