Anionex/agent-vision-toolkit

1,125 stars · Last commit 2026-08-27

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

README preview

<p align="center">
  <img src="assets/hero.png" alt="agent-vision-toolkit — Give text-only LLM agents eyes." width="100%">
</p>

<div align="center">

# agent-vision-toolkit
<a href="https://trendshift.io/repositories/99395?utm_source=trendshift-badge&amp;utm_medium=badge&amp;utm_campaign=badge-trendshift-99395" target="_blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/trendshift/repositories/99395/daily?language=Python" alt="Anionex%2Fagent-vision-toolkit | Trendshift" width="250" height="55"/></a>


[![X (Twitter)](https://img.shields.io/badge/-@anion__ex-000000?style=flat-square&logo=x&logoColor=white)](https://x.com/anion_ex)
[![GitHub stars](https://img.shields.io/github/stars/Anionex/agent-vision-toolkit?style=flat-square&logo=github)](https://github.com/Anionex/agent-vision-toolkit/stargazers)
[![GitHub forks](https://img.shields.io/github/forks/Anionex/agent-vision-toolkit?style=flat-square&logo=github)](https://github.com/Anionex/agent-vision-toolkit/forks)
[![License: MIT](https://img.shields.io/github/license/Anionex/agent-vision-toolkit?style=flat-square&color=4EAA25)](https://github.com/Anionex/agent-vision-toolkit/blob/main/LICENSE)

[![Agent Skills](https://img.shields.io/badge/Agent%20Skills-Standard-green?style=flat-square)](https://agentskills.io)
[![Extensions](https://img.shields.io/badge/-Extensions-3178C6?style=flat-square)](https://github.com/Anionex/agent-vision-toolkit/tree/main/extensions)
[![Shell](https://img.shields.io/badge/-Shell-4EAA25?style=flat-square&logo=gnubash&logoColor=white)](https://github.com/Anionex/agent-vision-toolkit/tree/main/bin)

**What it thinks is what it sees — give any text-only coding agent eyes: image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, as a vision toolkit plus a skill, with optional drop-in integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode.**

View full repository on GitHub →