Anionex/agent-vision-toolkit
Agent Vision Toolkit gives text-only LLM agents image QA, screenshot OCR, UI reconstruction, and GUI automation through a Python toolkit.
Excerpt
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 — ★ 512 · Python · topics: agent, agent-skills, claude-code, cli, codex, computer-use
Read at source: https://github.com/Anionex/agent-vision-toolkit