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.

CATEGORY

Vision & Media DSH plugins

Verified manifests and exact versions in this category.

All categories

All pluginsAgents & Orchestration1.5kMemory & Context2.1kCoding & Developer Tools4kUI & Customization5.6kIntegrations & Communication3kVision & Media912Search & Research1.2kSecurity & Access1.8kModels & Usage2.5kProductivity & Workflow3.6k

All plugins

910 plugins
Wv1.0.0
dsh-wallpaper-theme

Wallpaper Theme

Wallpaper-driven liquid glass theme for DeepSeek Harness: scan Wallpaper Engine or any folder, click to apply an image or video wallpaper, with adjustable wallpaper blur, surface opacity and glass blur.

↓ 0★ 0
Updated 9/27/2026
Av0.1.0
dsh-audio-converter

Audio Converter

Audio converter: decrypts encrypted music from platforms such as 网易云 NCM / 酷我 KWM / 酷狗 KGM / QQ音乐 QMC, converts between mp3/flac/m4a/aac/wav/ogg/opus, and provides audio enhancements including loudness normalization, EQ, dynamic compression, resampling, and bit depth adjustment. Includes a drag-and-

↓ 0★ 0
Updated 9/27/2026
Vv0.1.0
dsh-voice-transcribe

Voice Transcribe

Local audio/video transcription for dsh: decode QQ/微信-style SILK audio, then use faster-whisper to convert it to text, with no API costs.

↓ 0★ 0
Updated 9/27/2026
Vv0.3.0
dsh-vision-3090-fix

Vision 3090 Fix

Local reverse proxy plugin for DeepSeek Harness that caps images per request to 1 and drops pinned max_tokens, for self-hosted vLLM backends that reject prompts with more than one image or with prompt_tokens + max_tokens beyond max_model_len

↓ 0★ 0
Updated 9/26/2026
Vv0.3.0
@dsh-external/dsh-vision-bridge

Vision Bridge

DeepSeek Harness vision bridge: session screenshots route by model capability. Image-capable models receive attachments inline; text-only models see the standard placeholder, and the bridge reads the image through a vision-language model — on demand via the vision_bridge_read tool or automatically v

↓ 0★ 0
Updated 9/25/2026
v0.8.6
sh-volume-knob

Sh Volume Knob

Read the newest turn aloud from the DSH composer: a speaker button right of the microphone that reads from the start of your newest question, scrolls the page to that spot and marks it with a blinking caret on one click, stops on the next, picks any other reading start position on press-and-drag-rig

↓ 0★ 0
Updated 9/25/2026
Pv0.2.4
dsh-plugin-screenshot-ask

Plugin Screenshot Ask

DSH 截图提问插件：输入框相机按钮或 Ctrl+Shift+A → 自动最小化窗口 → 原生全屏框选浮层（确认/取消按钮）→ 选区直接作为图片附件进入当前会话输入框，全程不落盘。Screenshot-to-ask for DeepSeek Harness: the window hides, a native region overlay covers every monitor, and the crop lands in the composer as an image attachment.

↓ 0★ 0
Updated 9/24/2026
Cv0.1.0-rc.3
@zseven-w/dsh-computer

Computer

A headless-first macOS Computer Use driver for DeepSeek Harness with AX-first observations, window-bound multimodal evidence, host-owned approval, and evidence-backed action receipts

↓ 0★ 0
Updated 9/23/2026
Iv0.1.0
dsh-image-reader

Image Reader

DSH plugin that lets text-only models understand images through a separate vision model.

↓ 0★ 0
Updated 9/23/2026
Cv0.5.0
dsh-course-subtitles

Course Subtitles

DSH dual-half plugin: extract course video subtitles (DeepLearning.AI, YouTube, Bilibili, Coursera), rebuild them as whole sentences, translate line-by-line (EN/ZH), generate section headings, and publish one Feishu doc per lesson under a parent node. Also exports a Course Outline (video titles as p

↓ 0★ 0
Updated 9/23/2026
Vv1.1.0
dsh-vision-assist

Vision Assist

DeepSeek Harness vision assistant plugin: equips models without vision capabilities with a switchable multimodal recognition model. Images in the input box are automatically saved to disk and rewritten as text prompts; the main model can view images by calling the vision_recognize tool. The recognit

↓ 0★ 0
Updated 9/22/2026
Mv0.1.3
media-preview

Media Preview

DSH 插件：在聊天记录中自动将本地音视频/图片路径渲染为可播放的预览组件。When an assistant message or tool result contains a local media path, the path is replaced inline with a playable <audio>/<video>/<img> element backed by same-origin /api/media-preview/* route.

↓ 0★ 0
Updated 9/21/2026
v0.1.0
dsh-video-to-notes

Video To Notes

Opt-in DeepSeek Harness skill bundle that turns course, lecture, tutorial, documentary, meeting, and talk videos into structured study notes.

↓ 0★ 0
Updated 9/21/2026
Sv0.1.0
dsh-say

Say

Give your DSH agent a voice: speak text aloud through your speakers, with pluggable TTS engines (built-in system voices out of the box, GPT-SoVITS for character voices).

↓ 0★ 0
Updated 9/21/2026
Pv0.1.0
dsh-pdf-sign

Pdf Sign

PDF electronic signing for DeepSeek Harness: generate handwritten-style signature images, stamp them onto PDF pages, and apply PKCS#7 digital signatures with your own certificate. · DSH PDF 电子签名插件：生成签名图、PDF 盖章（可视化签名）、自签/自备证书的数字签名。

↓ 0★ 0
Updated 9/20/2026
Uv0.1.0
@dsh-external/ui-external-vision

Ui External Vision

External vision model plugin for image recognition when the active model lacks vision

↓ 0★ 0
Updated 9/20/2026
Dv0.1.1
@dsh-external/dsh-drop-to-path

Drop To Path

Drop or paste images, PDFs, office docs, zips, videos and audio into the DSH composer as workspace file paths instead of model attachments — lets a text-only model agent read them via vision tools.

↓ 0★ 0
Updated 9/18/2026
Cv0.2.0
dsh-cad-viewer

Cad Viewer

dsh plugin: a 3D model library and a three-cad-viewer workbench in a '3D模型' tab, plus inline model cards and CadQuery agent tools. Models are stored server-side, so the library is shared across devices.

↓ 0★ 0
Updated 9/18/2026
Dv1.0.0
deepseek-media-gallery

Deepseek Media Gallery

DSH plugin: browse, preview, download and delete generated images and videos from a sidebar popup.

↓ 0★ 0
Updated 9/16/2026
Vv0.3.0
@achasoft/dsh-voice

Voice

Voice input for the DeepSeek Harness Web Client: a microphone control in the composer, a transcription capability seam, and two selectable providers

↓ 0★ 0
Updated 9/15/2026
Sv0.1.0
dsh-screen-eye

Screen Eye

Autonomous screen vision for DeepSeek Harness on macOS: the agent captures the screen and receives the image itself in one call.

↓ 0★ 0
Updated 9/15/2026
Uv0.1.0
dsh-upload-plugin

Upload Plugin

DeepSeek Harness plugin providing Add photos, Add files, and Uploaded files in chat UI with vision validation and session isolation

↓ 0★ 0
Updated 9/14/2026
Ev0.1.0
expense-capture

Expense Capture

Turn receipts and invoices into ledger-ready expense rows without invention: every field (date, merchant, amount, currency, tax) traces to the source image, unclear fields are flagged not guessed, currency and tax treatment are stated, and the batch ends with a reconciliation of count and total agai

↓ 0★ 0
Updated 9/14/2026
Iv0.4.1
dsh-image-annotate

Image Annotate

DSH web plugin: click a pending image in the composer to annotate it (pen, box, arrow, and movable/resizable text frames) and insert the annotated PNG back as a new attachment.

↓ 0★ 0
Updated 9/14/2026
Tv3.0.0
taishan-vision

Taishan Vision

Taishan Vision - Enables DeepSeek Harness text-only models to understand images: GLM visual recognition + inference by the selected model (static plugin package, permanently effective after restart; modified by JingQing v1.1.8)

↓ 0★ 0
Updated 9/14/2026
Iv0.1.0
@zivye/dsh-img-save

Img Save

Hover-to-download buttons for images in DeepSeek Harness conversations.

↓ 0★ 0
Updated 9/13/2026
Iv0.6.1
dsh-image-governor

Image Governor

Session image payload governor for DeepSeek Harness: audit which images a session still ships, pick the ones to keep, and move the rest out of the model context.

↓ 0★ 0
Updated 9/12/2026
Mv1.4.0
dsh-media-inline-preview

Media Inline Preview

All-in-one inline media for DeepSeek Harness chat: ```mip-img / ```mip-video / ```mip-audio fences render images (cards + lightbox + grids, TGA→PNG), native <video> and <audio> players right inside the message (house pattern of img-preview/dsh-mermaid/pbr-render). Image route whole-reads local works

↓ 0★ 0
Updated 9/12/2026
Iv0.1.0
dsh-image-base64

Image Base64

DeepSeek Harness plugin: transcodes images to a base64-safe format (PNG) before a vision request, fixing gateways like LM Studio that reject non-PNG/JPEG/GIF data URLs with "'url' field must be a base64 encoded image."

↓ 0★ 0
Updated 9/12/2026
Iv0.2.0
dsh-image-format-converter

Image Format Converter

Convert model-bound images to JPEG/PNG/WebP for LM Studio compatibility

↓ 0★ 0
Updated 9/12/2026
← Previous1…2425262728…31Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in