Vision & Multimodal

dsh-vision-toolkit

dsh-external/dsh-vision-toolkit

dsh-external

DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A.

Repository is no longer available (checked 2026-11-15). This entry is retained for tracking and cannot be installed.

Repository

License: Unknown
Added: 2026-08-17
Maintenance: missing
Install kind: github

Manifest details

Manifest status: Not verified
Manifest path: -
Manifest checked: 2026-08-17
Lifecycle scripts: None found

Static manifest checks report declarations only; they are not compatibility or security review.

README

Source README · Read Chinese README

No README content is available.

Vision & Multimodal

dsh-plugin-browserskill

Tencent

Tencent/BrowserSkill/packages/dsh-plugin-browserskill

BrowserSkill 的 DeepSeek Harness 浏览器自动化桥接插件，通过原生浏览器工具控制可见的 Chrome 和 Edge Agent Window，支持可访问性与 VOM 页面观察、截图、隔离的多会话控制和 Web UI 实时观察浮层。

View details

☆ 10,413github+ 08-21

Vision & MultimodalCurated

modlens

liustack

liustack/modlens

为纯文本模型架起视觉桥梁：粘贴图片，输出结构化 JSON 证据（OCR、版面、语义）。

View details

☆ 4,975npm+ 08-14

Vision & MultimodalCurated

dsh-vision-router

ysr666

ysr666/dsh-vision-router

为纯文本 Agent 提供视觉能力：内置免 Key 视觉链 + 像素级视觉工具（看图问答、定位、裁剪、像素对比、取色、OCR、矢量化、抠图、截图）；粘贴图片即可用。

View details

☆ 1,271github+ 08-14

Vision & Multimodal

dsh-windows-mcp

helloHub1212

helloHub1212/dsh-windows-mcp

Windows desktop automation for DeepSeek Harness — plugs CursorTouch/Windows-MCP (screenshot, UI automation, input, clipboard, processes, registry) into DSH through the official MCP client bridge.

View details

☆ 1,220github+ 10-30

Vision & MultimodalCurated