Discover The Best DSH plugins

Vision tools · DeepSeek Harness plugins — Page 40

1453results

Find image understanding, screenshot analysis and visual interaction plugins; compare inputs and usage.

dsh-atlascloud

Atlas Cloud skills and opt-in MCP tools for DeepSeek Harness.

Skills · Agent collaboration · Vision tools · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AtlasCloudAI/dsh-atlascloud
dsh-attach-picker

DSH Web 输入框工具栏图片按钮:点击用系统文件选择器挑图片,不用拖拽。Toolbar button that opens the OS file picker to attach images to the DSH Web composer — no drag-and-drop needed.

Vision tools · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qwerty-k-de/dsh-attach-picker
dsh-attachment-downscale

附件自动降级:DSH 图片准入(单边 ≤2000px / ≤3.5MB / ≤4000万像素)超限图片不再拒绝,用 sharp 自动缩小/重编码后入库,用户上传手机原图不再踩线。

Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:zoumutou/dsh-attachment-downscale
dsh-attachment-formats

Codex-style attachment format expansion for the DeepSeek Harness Web GUI: PDF text-layer extraction (pymupdf4llm / pdfjs), Office text extraction, long-document spill + index cards, scanned-PDF OCR (tesseract.js), and browser-decodable images to PNG.

Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:genusamblyrhynchusbrunooftoul602/dsh-attachment-formats
dsh-attachment-formats

Codex-style attachment format expansion for the DeepSeek Harness Web GUI: PDF text-layer extraction (pymupdf4llm / pdfjs), Office text extraction, long-document spill + index cards, scanned-PDF OCR (tesseract.js), and browser-decodable images to PNG.

Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:linkingoscar/dsh-attachment-formats
dsh-auto-vision

Bridges images into text for DeepSeek Harness: when the session's selected model cannot see images, a configured vision model describes them and the descriptions enter the durable session history as folded context rows — your message stays untouched.

Vision tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:soarGuo/dsh-auto-vision
dsh-awesome-model-setting

DeepSeek Harness web plugin: a Model Capabilities settings page for declaring model input modalities, context window, output cap and image budgets without hand-editing settings.yaml.

Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Kazusa1085/dsh-awesome-model-setting
dsh-background

Custom background wallpaper for the DeepSeek Harness chat page — upload a local image or paste an image link, tune opacity and brightness, scope to chat area or full screen.

Vision tools · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lcohvne-tomorin/dsh-background
dsh-baidu-ocr

Baidu cloud OCR (PaddleOCR-VL + Unlimited-OCR) for DeepSeek Harness Web: drag images/PDFs in, OCR to markdown, write results as local files.

Vision tools · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:pipiwolve/dsh-baidu-ocr
dsh-balance-vision

DeepSeek 余额实时显示插件(含视觉模型): 在 dsh Web UI 输入框下方的统计条实时显示账户余额与本次对话的估算消耗, 内置 deepseek-v4-flash / deepseek-v4-pro / deepseek-v4-flash-vision-exp 官方峰谷定价

Vision tools · Financial data · Interface extensions · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Flonger/dsh-balance-vision
dsh-baoyu-skills

宝玉技能库(移植自 JimLiu/baoyu-skills)

Skills · Vision tools · Developer tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:GongYuanCaiJi/dsh-baoyu-skills
dsh-base64-file

Base64 文件转换:文件 ↔ base64/data URL(图片嵌入 HTML/JSON)

Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-base64-file
dsh-bg-changer

DeepSeek Harness background wallpaper plugin: upload an image and tune fit/scale/position/opacity/blur plus interface translucency, from a row at the bottom of Settings > General.

Vision tools · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:GIN0076/dsh-bg-changer
dsh-bg-image

Custom background image for the DeepSeek Harness web UI (theme token overlay + settings card)

Vision tools · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:mhwww/dsh-bg-image
dsh-bg-new

DSH 插件:给 DeepSeek Harness 换网页界面背景(系统预设/纯色/渐变/图片/视频)。侧栏「壁纸」按钮弹出右侧抽屉,滚轮+拖动的小图同时管缩放与定位,支持毛玻璃质感、本地媒体伺服、客户端即时生效并持久化到 settings;模型也可用 bg_apply 工具直接换。

Vision tools · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sz1698/dsh-bg-new
dsh-bg-plugin

DSH 自定义背景插件:为 DSH Web GUI 应用远程 URL 图片或本地图片作为背景,支持清晰度/压暗/模糊调节,设置面板保持默认外观。

Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiaoxingyuemiao/dsh-bg-plugin
dsh-bg-skin

背景皮肤:将 DSH 界面背景替换为随插件分发的默认图片(assets/ds.jpeg,安装即用),可选 imagePath 覆盖,缺图自动回退默认皮肤。

Vision tools · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jinzhengen964-cmyk/dsh-bg-skin
dsh-bridge-preview

为 dsh-tool-vision 桥接导出的图片提供对话内联预览:用户粘贴的图片在气泡中显示缩略图,不改变桥接文本与模型行为

Vision tools · Interface extensions · Integrations
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xing666173/dsh-bridge-preview
dsh-browser

AI 浏览器操作:CDP 直连 Chrome,文本 snapshot+ref 主感知,截图走辅助视觉兜底

Vision tools
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:statem-li/dsh-browser
dsh-browser

Browser automation for the DeepSeek Harness: CDP-driven tools that navigate, click, type, and read a real Chrome, with screenshots rendered inline in the conversation

Vision tools · Developer tools · Productivity
dsh-browser-bridge

DeepSeek Harness plugin + browser extension bridge: lets DSH agents read and control the user's browser, like Kimi WebBridge or Claude's browser extension. Node side: browser_* tools over a localhost WebSocket; browser side: a Manifest V3 extension.

Agent collaboration · Vision tools · Integrations
dsh-browser-bsk

Browser automation for DeepSeek Harness via bsk — navigate, snapshot, click, fill, and screenshot the user's real browser.

Vision tools · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ylwl1997/dsh-browser
dsh-browser-verify

Read-only browser verification tools for the DeepSeek Harness web GUI: browser_open / browser_mock / browser_assert / browser_screenshot — verify a page (H5/desktop) in ≤4 tool calls with mock interception, DOM assertions, and screenshots that auto-project into the model context.

Vision tools · Interface extensions
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:1710782766/dsh-browser-verify
dsh-browser-vision

Browser tool for DeepSeek Harness that can see the page: drives a real Chrome over CDP with browser-use and reads it with deepseek-v4-flash-vision-exp, so canvas text, text inside images and rendered charts are readable. Schema-driven JSON extraction, Markdown output, and per-run token/cost accounting.

Vision tools · Financial data · Productivity
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tristan-mcinnis/dsh-browser-vision

Find the right plugin, then get started

  1. Search by task

    Use a feature keyword or category, then sort by recent updates or GitHub stars.

  2. Explore capabilities

    Read the description, AI analysis and original README to understand what a plugin does.

  3. Check and install

    Review compatibility, dependency ranges and instructions, then copy the available install command.

Questions about DSH Hub

What is DSH Hub?

DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.

Does inclusion mean a plugin is tested and compatible?

No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.

How do I install a plugin?

Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.