agent-vision-toolkit

SkillGitHubActivePython

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

Description provenance: Original source

Open canonical source

Measured: Oct 22, 2026 · 71 observations

Domains & Uses

Domains: Agents, skills and MCP
Uses: Agent skills, Code assistants

Installation

git clone https://github.com/Anionex/agent-vision-toolkit ~/.claude/skills/agent-vision-toolkit

Check at the source

Compatibility and prerequisites must be checked in the official documentation.

https://github.com/Anionex/agent-vision-toolkit

Classifications

Nature: Tool

Measurement history

Comparable readings are grouped by signal and unit.

Stars

1,241stars · Oct 22, 2026

+9 (+0.7 %)since Oct 15, 2026

Exact values · 8 readings

Measured	stars	Change
Oct 22, 2026	1,241	+4
Oct 21, 2026	1,237	-1
Oct 20, 2026	1,238	+4
Oct 19, 2026	1,234	0
Oct 18, 2026	1,234	0
Oct 17, 2026	1,234	+1
Oct 16, 2026	1,233	+1
Oct 15, 2026	1,232	·