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 automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
ORIGINAL REPOSITORY
Anionex/agent-vision-toolkit ↗GitHub activity
- Stars
- 1,254
- Forks
- 50
- Open issues and PRs
- 8
- Repository size
- ~27,471 KB
- Default branch
- main
- Created
- Aug 1, 2026
- Repository updated
- Nov 3, 2026
- Last push
- Oct 13, 2026
- Language
- Python
- License
- MIT
Topics agent · agent-skills · claude-code · codex · computer-use · deepseek · dsh-plugin · glm · harness-engineering · multimodal · opencode · text-only-llm
Repository-wide figures from GitHub, checked Nov 3, 2026. Stars are endorsements, not a Mega AI Hub quality rating. Repository size is GitHub’s estimate; a ZIP download may differ.
Resource information
- Original repository
- Anionex/agent-vision-toolkit
- Credit basis
- GitHub repository owner or organization; individual authorship is not asserted
- Publisher
- Anionex
- Upstream last modified
- Nov 3, 2026
- Official website
- https://github.com/Anionex/agent-vision-toolkit
- Languages
- Python
- Access
- Open original GitHub repository; publisher terms apply
- Last checked
- Nov 3, 2026
- License
- MIT
- Last record update
- Nov 3, 2026