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
Anionex/agent-vision-toolkit
View on GitHub ↗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
agent-vision-toolkit grew +2.0% in the last 30 days, ranks 495th of 2,792 in Agent SDK / Framework, last commit 38 days ago.
Star trajectory
81 days tracked+2.0% in 30d, above the Agent SDK / Framework median of +1.5%.
Last commit 38 days ago, staler than the median of 14d.
How it compares in Agent SDK / Framework
Ranked 495th of 2,792 by stars.
Related repos
Ranked by shared tags, then keywords, then starsWhere agent-vision-toolkit sits
Hover or focus a node for details. Click to open it.
- This repo
- Related repo
- Tag or category
Community plugin to control Blender 3D with any LLM of your choice. Not affiliated with the official Blender…
+3.3k (+10%) in 30d · Committed 2d ago · Python · MIT
Shares Tools & Integrations, Computer & Browser Use, Voice / Vision I/O, Agent SDK / Framework
Pluggable extension packages for the Pi AI-agent runtime. Each package exposes LLM-callable tools via MCP —…
+9 (+11%) in 30d · Committed yesterday · TypeScript · Apache-2.0
Shares Agent SDK / Framework, Tools & Integrations, Computer & Browser Use, Voice / Vision I/O
AIHawk: AI job application bot, automated job search, job hunting, auto-apply to resume-matching jobs while…
+381 (+1.2%) in 30d · Committed today · Python · MIT
Shares Agent SDK / Framework, Tools & Integrations, Computer & Browser Use, Voice / Vision I/O
One command for every interface—search, run, and inspect real software across APIs, browsers, desktops, local…
-3 (-1.3%) in 30d · Committed 4d ago · TypeScript · Apache-2.0
Shares Agent SDK / Framework, Tools & Integrations, Computer & Browser Use, Voice / Vision I/O
System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and…
+17 (+10%) in 30d · Committed today · Python · Apache-2.0
Shares Agent SDK / Framework, Computer & Browser Use, Voice / Vision I/O, Tools & Integrations
Yosuri — LESS CHAT, MORE AUTOMATIC. A 24H self-evolving AI agent that aggregates free models into one OpenAI &…
-1 (-1.1%) in 30d · Committed 18d ago · Go · AGPL-3.0
Shares Agent SDK / Framework, Voice / Vision I/O, Computer & Browser Use, Tools & Integrations
The open-source Devin alternative. Run Claude Code, Codex or OpenCode in isolated cloud workspaces you can…
-1 (-0.3%) in 30d · Committed 7d ago · TypeScript · AGPL-3.0
Shares Agent SDK / Framework, Computer & Browser Use, Tools & Integrations
Computer-Use SDK for E2E QA Testing
-133 (-28%) in 30d · Committed 60d ago · JavaScript
Shares Agent SDK / Framework, Computer & Browser Use, Tools & Integrations
为 Claude Code 赋能多模态视觉能力,适配 纯文本 LLM 底座,用于截图 / UI / 图表分析;搭配 browser-harness 可做前端布局自动化检查。
+2 (+1.2%) in 30d · Committed 88d ago · Python · MIT
Shares Tools & Integrations, Voice / Vision I/O, Agent SDK / Framework
Pie – free, open-source AI browser agent for Chrome. Reads pages & PDFs, fills forms, extracts data, automates…
+7 (+8.0%) in 30d · Committed yesterday · TypeScript · Apache-2.0
Shares Agent SDK / Framework, Computer & Browser Use, Tools & Integrations
- Language
- Python
- License
- MIT License
- Contributors
- 8
- Forks
- 50
- Watchers
- 5
- Open issues
- 4
- Releases
- 2
- Created
- 2026-08-01
- Stars this week
- +4
You've seen where agent-vision-toolkit stands today.
Get the moves before everyone else: the 5 Agent SDK / Framework repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.