CordisPluginGuide & Directory
English简体中文한국어

237229953-create / dsh-vision

Listed

DSH plugin: text-only models (e.g. DeepSeek-V4) automatically see images via a vision model. Official surface-replace, cache-friendly, human transcript untouched. 纯文本模型自动识图桥

masterModelTool View source

Installation

npx -y @deepseek-ai/dsh plugin --profile web add github:237229953-create/dsh-vision

This installation command is an unverified starting point generated from the GitHub repository address.

Repository information

Language
JavaScript
License
MIT
Last updated
Aug 14, 2026, 11:27 AM

Install deliberately

Review source code, permissions, lifecycle hooks, dependencies and network access. Test untrusted plugins in an isolated environment.

Related plugins

More plugins

View all plugins

agent-vision-toolkit

Model · Tool · Skill

819

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

npx -y @deepseek-ai/dsh plugin --profile web add github:Anionex/agent-vision-toolkit
GitHub installView details

dsh-visual-plugin

Model · Tool

4

Dsh-visual-plugin.Give your text-only model eyes: forward user images to any OpenAI-compatible vision model and see the results in a Web UI right panel

npx -y @deepseek-ai/dsh plugin --profile web add github:jyh20030112/dsh-visual-plugin
GitHub installView details

vision_kit

Model · Tool

0

Make your AI agent a math tutor. Structured extraction of vectors, matrices & geometry from math figures, with dimension-consistency + geometric self-check. Vision plugins for DeepSeek Harness, opencode (MCP) & CLI. Verify, don't believe.

npx -y @deepseek-ai/dsh plugin --profile web add github:Seom-ingit/vision_kit
GitHub installView details

modlens

Model · Tool · Skill

1252

The first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网第一个 DeepSeek Harness 视觉插件，为 DeepSeek、GLM 等纯文本模型外挂视觉能力，粘贴图片即得结构化 JSON 证据（OCR、版面、语义）。

npx -y @deepseek-ai/dsh plugin --profile web add github:liustack/modlens
GitHub installView details

dsh-vision

Model · Tool

9

为 DeepSeek Harness 增加外挂识图模型：圆形鲸鱼按钮、发送图片识图自动回传、模型自主截图+识图工具、多协议自动适配、小白一键安装（未装 Node.js 自动下载）

npx -y @deepseek-ai/dsh plugin --profile web add github:linenxi-ctrl/dsh-vision
GitHub installView details

dsh-drop-to-path

Model · Tool

6

DSH 插件:图片与文件直达纯文本模型——图片保留原生附件体验,PDF/Office/压缩包/视频/音频显示为附件栏方块,点击发送时自动转为工作区路径,配合 dsh-vision-toolkit 粘贴即看图。A DSH plugin that delivers images AND files to text-only models as workspace paths: images keep the native attachment UI, other files show as square chips in the rail, paths append on send — pairs with dsh-vision-toolkit.

npx -y @deepseek-ai/dsh plugin --profile web add github:loudMore/dsh-drop-to-path
GitHub installView details