DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Vision — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
V

@zenk/vision

Vision

DSH local vision capabilities: macOS Vision OCR + ollama qwen3-vl semantic description + uploaded image bridge (converts image blocks to text, available on text-only channels)

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:kaaaaahn/dsh-vision#33b5b19a21a09ab41200489fa8ec085cc5fdea30
READMECompatibilityVersions

Compatibility and provenance

Vision is published as @zenk/vision and currently resolves to version 0.3.1. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated
8/24/2026

Versions

0.3.1stable
8/24/2026

Related plugins

Loading related plugins…

Latest
0.3.1
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
any
License
Not declared
Source
github
GitHub
★ 1
Weekly downloads
0
Last push
8/24/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in vision-media.

Tool Describe Image@linxin666/dsh-tool-describe-imageModel-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable — Modlens@liustack/modlensPlug-in vision for text-only LLMs, powered by the free Antigravity CLIDeepseek Ivideodeepseek-ivideoiPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.Image Gendsh-image-genBring ChatGPT-like image generation to DeepSeek Harness — Gemini, OpenAI, Seedream, DashScope, local ComfyUI & more.

README

@zenk/vision

DSH 本地视觉插件：对话框里直接粘贴截图，AI 就能看到并分析，图片不出本机。

特性

  • OCR 带像素坐标（macOS Vision）：识别文字并给出位置，UI 定位直接按坐标说
  • 语义理解（ollama + qwen3-vl）：看懂画面布局、元素与异常区域
  • 零配置：自动检测环境、按内存选模型（8G→2b / 16~32G→4b / 32G+→8b）、缺 ollama 自动安装
  • 渐进可用：模型后台下载（1.8~5.7GB）期间 OCR 已可用
  • 全本地：免费、离线、图片不出 Mac

安装

dsh plugin --profile web add "github:kaaaaahn/dsh-vision#v0.3.1"

重启 DSH 生效。桌面端把 --profile web 换成 --profile desktop。

插件市场条目（添加来源 https://kaaaaahn.github.io/dsh-vision/catalog/source.json）依赖 npm 发布，目前暂未上线，请使用上方 GitHub 命令安装。

首次使用会自动下载模型（后台进行），期间 OCR 已可用；环境细节见 docs/ollama-setup.md。

使用

  • 直接粘贴图片发送，AI 自动分析并回复
  • 或让 AI 调用 vision_analyze(file_path=..., describe=true) 分析本地文件（describe 开启语义描述）

文档

  • 环境准备与模型选型
  • 常见问题（22 条 FAQ）

仓库结构

├── lib/
│   ├── index.js              # 插件入口：vision_analyze + vision_setup + 图片桥接 + guard
│   └── vision_analyze.swift  # OCR + ollama 语义描述脚本（随包分发）
├── catalog/                  # DSH Community Market 目录源
├── docs/
│   ├── ollama-setup.md       # 环境准备参考
│   ├── troubleshooting.md    # 常见问题 FAQ
│   └── PUBLISHING.md         # 维护者内部文档（发布流程）
└── package.json

License

MIT