Anionex/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
- Stars
- 1.2k
- Forks
- 50
- Open issues
- 4
- Last push
- 10d ago
About agent-vision-toolkit
agent-vision-toolkit is a free, open-source AI coding tool by Anionex, written mainly in Python. 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. It has 1.2k GitHub stars and 50 forks, and was last updated 10d ago. It's released under the MIT license, a standard open-source license.
- License
- MIT
- Language
- Python
- Stars
- 1,247
- Last update
- 10d ago
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not stated
- Self-hostable
- Not stated
Similar free tools
claude-mem102k stars · Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Cla
archify88k stars · Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
Understand-Anything88k stars · Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI,
agent-skills110k stars · Production-grade engineering skills for AI coding agents.
claude-skills29k stars · 380 Claude Code skills & agent skills & plugins (30+ Agents, 70+ custom commands, 380+ skills, customizable references, scripts)for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — e
open-design103k stars · The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. Sha
agent-vision-toolkit FAQ
Is agent-vision-toolkit free?
Yes. agent-vision-toolkit is open source and free to use. It's released under the MIT license, a standard open-source license.
Does agent-vision-toolkit run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does agent-vision-toolkit need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is agent-vision-toolkit still maintained?
Yes. It was last updated 10d ago and has 4 open issues on GitHub.
What are alternatives to agent-vision-toolkit?
Similar free, open-source tools include claude-mem, archify, Understand-Anything, agent-skills.