agent-vision-toolkit
Gives text-only AI coding agents the ability to understand images by handling image Q&A, screenshot OCR, and UI recognition outside the model itself.
View anionex/agent-vision-toolkit on GitHub- GitHub stars
- 1,262
- Forks
- —
- Language
- Python
Project details
- Repository
- anionex/agent-vision-toolkit
- Licence
- MIT
- Primary language
- Python
- Catalog status
- Available
- Catalog check
- 2026-11-13
Repository description
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
Explore by topic
More tools in AI agents
- archify
tt-a1i · Apache-2.0
Turns a codebase or a plain-language system description into a polished, interactive architecture diagram (self-contained HTML/SVG, exportable to PNG/SVG/WebM) directly…
- dsh-vision-toolkit
anionex · MIT
dsh-vision-toolkit adds a real vision toolbox to text-only AI agents: paste an image for recognition, multi-image Q&A, screenshot-to-UI restoration, and pixel-level…
- agents
wshobson · MIT
A one-stop marketplace of ready-made AI coding agents, skills, and commands you can install into Claude Code, Cursor, Codex, or five other AI coding tools with a single…
- geo-sleuth
oldcircle · MIT
Hand an AI agent a photo with no text, plates, or landmarks and one sentence -"find where this photo was taken"- and it uses map geometry, elevation data, and satellite…