Home› Projects› agent-vision-toolkit
agent-vision-toolkit
Python

agent-vision-toolkit

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, C

by Anionex · GitHub
1.1k
Stars
38
Forks
+178 this week
Trending
MIT
License
2026
Created
3 days ago
Last commit
agent
Category
Python
Language
agentagent-skillsclaude-codeMITPython
View on GitHub
In plain words

Equip text-only coding agents with image processing abilities like answering questions about images and understanding screenshots.

✓ Claimed by its maintainer
agent-vision-toolkit — GitHub preview card
📈 Star history
1k0k
2026-08-102026-08-31
📈 Track agent-vision-toolkit

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

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, C

agent-vision-toolkit has 1.1k stars on GitHub. It has been forked 38 times. agent-vision-toolkit is written mainly in Python. It has been in active development since 2026. agent-vision-toolkit is available under the MIT license. Its main topics are agent, agent-skills, claude-code, codex.

❓ Frequently asked questions

What is agent-vision-toolkit?

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, C

Is agent-vision-toolkit open source?

agent-vision-toolkit is an open-source project. It is released under the MIT license.

Is agent-vision-toolkit free?

Yes. agent-vision-toolkit is free and open source — you can use, modify and self-host it.

What license does agent-vision-toolkit use?

agent-vision-toolkit is available under the MIT license.

What language is agent-vision-toolkit written in?

agent-vision-toolkit is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — agent-vision-toolkit

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=anionex-agent-vision-toolkit)](https://olud.ai/project/anionex-agent-vision-toolkit.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
modlens
The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding…
★ 3.8k · agent-skills
sharestext-only-llmvision
codex-vision-proxy
让纯文本模型在 Codex 中无障碍看图(view_image)的更优方案，附为纯文本 LLM 设计的视觉工具包&skill ｜ A superior approach for enabl…
★ 273 · agent
sharesglmharness-engineering
dsh-vision-complete
给 DeepSeek 补上「眼睛和耳朵」的多模态视觉插件：看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读，一键安装（DSH 插件）。
★ 42 · dashscope
sharesvisiondsh-plugin
claude-code-vision-skill
为 Claude Code 赋能多模态视觉能力，适配 纯文本 LLM 底座，用于截图 / UI / 图表分析；搭配 browser-harness 可做前端布局自动化检查。
★ 171 · agent-skills
sharesvisiondeepseek
GLM-skills
Official skills for the GLM family of models.
★ 468 · glm
sharesvisionglm
dsh-vision-router
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level v…
★ 1k · deepseek-harness
sharesvisiondsh-plugin
dsh-vision
Near-native image understanding for DeepSeek Harness
★ 88 · deepseek-harness
sharesvisiondsh-plugin
Thinking-with-Visual-Primitives
Archived snapshot of Thinking-with-Visual-Primitives
★ 276 · deepseek
sharesvision-language-modeldeepseek
JavaGuide
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
★ 157k · agent
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborativ…
★ 154k · agent

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.