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...

by anionex Python MIT licence 50 forks Created Aug 2026 View on GitHub

Stars
1,260
7% of Anionex's stars
Rank
#54,110
of 852,204 repos, top 7%
In Python
#9,741
of 173,304 repos, top 6%

Among 852,204 repos

Compare with

1k–1.6k stars: 23,672 repos, including agent-vision-toolkit

Stars along the bottom, and repos in each band on a log scale

Quick stats

Next rank
+1 star to reach #54,077
Next milestone
+5,951 stars to reach the top 1%
Popular
One of 66,543 repos with 1k+ stars

Stars counted Recounted daily Next count around