BetaRare
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
- Owner
- Anionex (personal account)
- Stars
- Stars: 1,254
- Forks
- Forks: 50
- Language
- Python
- License
- MIT
- Created
- 2026
- Topics
- codexagentdeepseekglmmultimodalagent-skillsharness-engineeringclaude-codecomputer-useopencode
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by Anionex
All 4 repos by Anionex- Anionex/banana-slidesStars: 15,939TypeScriptStable
- Anionex/dsh-vision-toolkitStars: 922TypeScriptBeta
- Anionex/dsh-turn-rewindStars: 144JavaScriptPrototype
Nearby in Python
All Python repos- bowang-lab/MedRAXStars: 1,254PythonBeta
- diodiogod/TTS-Audio-SuiteStars: 1,254PythonBeta
- chunxiaoxx/nautilus-compassStars: 1,254PythonBeta
- RobotWebTools/rosbridge_suiteStars: 1,254PythonBeta
- brian-team/brian2Stars: 1,254PythonBeta
- maciejkula/glove-pythonStars: 1,254PythonBeta