agent-vision-toolkit

by Anionex · Skills & Agents

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

View on GitHub Homepage

Related project

Carries a dsh topic on GitHub without any plugin wiring we could detect. Useful to know about, but it will not load as a plugin.

We found no cordis.yml, no dependency on the Cordis runtime, and no dsh package naming in this repository.

Installing

No published npm package was found. Clone the repository and follow its README to build from source.

Repository details

Stars: 512
Forks: 22
Open issues: 4
Language: Python
License: MIT
Created: 2026-08-01
Last push: 2026-08-13

Topics

agentagent-skillsclaude-codeclicodexcomputer-usedeepseekdsh-pluginglmharness-engineeringkimillmmultimodalopencodetext-only-llmvisionvision-language-model

More in Skills & Agents

dsh-cc-tui

Verified

ccch1mneyyy

DSH 官方尚无终端 TUI 的补位之作：Claude Code 风格全屏交互终端插件——像素鲸鱼顶栏、实时工作状态行、思考流式展开、双击 Esc 回滚、上下文进度条 + TPS 仪表。npm 一键安装。

188TypeScriptupdated today

dsh-vision-toolkit

Verified

Anionex

让纯文本模型更好地做视觉任务的DeepSeek Harness插件：带意图的图片问答、长截图 OCR、UI 还原等｜DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.

142TypeScriptupdated today