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 & Media DSH plugins — Page 3

CATEGORY

Vision & Media DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1029Memory & Context1283Coding & Developer Tools2785UI & Customization3643Integrations & Communication1892Vision & Media612Search & Research864Security & Access1270Models & Usage1665Productivity & Workflow2221

All plugins

613 plugins
v0.1.2-rc.1
dsh-open-file

Open File

Workspace-bound arbitrary file upload, reading, OCR, and rendering for DeepSeek Harness.

vision-mediaproductivity-workflow★ 5↓ 177
Updated 10/16/2026
v0.10.0
dsh-vision-fallback

Vision Fallback

DSH Silent Vision Enhancement: Select the main model as usual; images are automatically sent to a fixed vision model and returned to the main model as hidden context.

vision-media★ 2↓ 333✓ v0.10.0 scan passed
Updated 10/16/2026
v0.4.12
dsh-voice-alert

Voice Alert

让 DSH 干完活会开口说话：回合结束自动播报「完成/失败/审批」，零配置内置 20 个音效，也可克隆自己的音色。| Make DSH speak when the job is done: auto voice alerts for done/failed/approval, 20 built-in sounds, or clone your own voice.

integrations-communicationvision-media★ 0↓ 975✓ v0.4.12 scan passed
Updated 10/16/2026
v0.2.1
dsh-tool-generate-image

Tool Generate Image

Model-facing generate_image tool for DeepSeek Harness (dsh): generates brand-new images with the Google Gemini image-generation service via the Antigravity CLI, saves them, and returns the paths. Hot-pluggable — install with `dsh plugin --profile web add

vision-mediamodels-usage★ 2↓ 318✓ v0.2.1 scan passed
Updated 10/16/2026
v0.2.22
dsh-draw

Draw

Unified static-image generation router for DeepSeek Harness: one image_generate tool with standard parameters, config-driven OpenAI-compatible engine routing (OpenAI Images, Zhipu CogView, and any compatible endpoint) with health-aware fallback, durable w

vision-media★ 0↓ 952
Updated 10/16/2026
v1.3.2
dsh-sound-lab

Sound Lab

DSH 声音工坊（Sound Lab）：Dialogue event sound effects, AI character voice generation, and sound library upload management, all through visual point-and-click controls; includes the 明日方舟安洁莉娜 desktop pet（60fps sprite animation, edge docking, and floating window configuration）. Hot-pluggable dsh plugin.

vision-mediaui-customization★ 2↓ 310
Updated 10/16/2026
v1.0.0
dsh-niulai-sound

Niulai Sound

牛来确认音 — DSH approval sound effects from the movie 《牛来》: plays 「妈妈」 when user confirmation is requested, interrupts it and plays 「牛来！」 the moment the user approves. 审批音效：请求确认时播放「妈妈」，批准瞬间掐断并播放「牛来！」。

vision-mediaintegrations-communication★ 2↓ 285✓ v1.0.0 scan passed
Updated 10/16/2026
v3.3.3
picturereader

Picturereader

Unified image understanding plugin for DeepSeek Harness (DSH). Visual twin adapter for native thumbnails + auto-analysis on any text-only model (incl. pi-ai providers); privacy/smart/strict routing; local tools (scan/OCR×4 engines (windows/macos/paddle/ra

vision-media★ 0↓ 816✓ v3.3.3 scan passed
Updated 10/16/2026
v0.2.0
dsh-web-voice-input

Web Voice Input

Voice input for the DeepSeek Harness (DSH) Web GUI: a microphone button in the chat composer that records audio, transcribes it through an OpenAI-compatible Whisper API (Groq / OpenAI / SiliconFlow), and inserts the recognized text into the input box.

vision-media★ 2↓ 269✓ v0.2.0 scan passed
Updated 10/16/2026
v0.2.8
dsh-mindseye

Mindseye

MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness

vision-media★ 1↓ 391✓ v0.2.8 scan passed
Updated 10/16/2026
v0.2.0
dsh-vision-recognizer

Vision Recognizer

Adaptive image routing for DeepSeek Harness: pass images directly to native multimodal models and transcribe them only for text-only models.

vision-mediamodels-usage★ 1↓ 390✓ v0.2.0 scan passed
Updated 10/16/2026
v0.8.2
@dttxorg/deepseekeyes

Deepseekeyes

Auditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.

vision-mediasecurity-access★ 7↓ 95
Updated 10/16/2026
v0.2.3
dsh-voice-talk

Voice Talk

Voice conversation mode for the DeepSeek Harness Web GUI: mic input with auto-submit, spoken readout of each reply's conclusion, and a hands-free multi-turn loop with barge-in.

vision-media★ 1↓ 375✓ v0.2.3 scan passed
Updated 10/16/2026
v0.7.0
dsh-tesseract-ocr

Tesseract Ocr

dsh plugin: recognize attached images locally with Tesseract OCR and send only the recognized text to the model. Text models never receive image bytes; vision passthrough is opt-in.

vision-media★ 5↓ 124✓ v0.7.0 scan passed
Updated 9/28/2026
v0.4.1
dsh-auto-vision

Auto Vision

DeepSeek Harness Vision Bridge: automatically discovers your configured multimodal models, equips text-only primary models with a vision tool, and returns recognition results as plain text. Zero configuration, one-command installation.

vision-media★ 1↓ 368
Updated 10/16/2026
v0.1.3
dsh-image-generation

Image Generation

DSH image generation plugin: Configure multiple image generation providers/models in settings and call the currently selected model in conversations via image_generate.

vision-media★ 0↓ 716✓ v0.1.3 scan passed
Updated 10/16/2026
v0.1.1
dsh-quicksight

Quicksight

Two-tier image reading for text-only models in DeepSeek Harness: fast local OCR (RapidOCR, offline) first, then a vision model via modlens as fallback.

vision-media★ 1↓ 352✓ v0.1.1 scan passed
Updated 10/16/2026
v0.5.0
dsh-vision-subagent

Vision Subagent

Capability-aware vision for DeepSeek Harness: native image input for multimodal models, with an isolated one-shot vision-route fallback for text-only models.

vision-mediaagents-orchestration★ 1↓ 335✓ v0.5.0 scan passed
Updated 10/16/2026
v0.4.1
dsh-vision-proxy

Vision Proxy

DeepSeek brain + automatic image transcription for DeepSeek Harness: a deepseek-vision provider route that transcribes attached images to text via any OpenAI-compatible VLM before delegating to the text-only DeepSeek adapter. Paid fast path with a key (Da

vision-mediamodels-usage★ 0↓ 661
Updated 10/16/2026
v0.1.7
dsh-subagent-vision

Subagent Vision

dsh bundle: subagent_vision — delegate image reading to a vision-capable model from a text-only session, plus paste-to-path so pasted images reach the subagent as file paths.

agents-orchestrationvision-media★ 1↓ 322✓ v0.1.7 scan passed
Updated 10/16/2026
v0.1.0
mimo-vision

Mimo Vision

DeepSeek Harness (DSH) native plugin: the describe_image tool, a vision bridge (image -> mimo-v2.5 -> text description) over the ctx.fs / ctx.credentials seams

vision-media★ 1↓ 319✓ v0.1.0 scan passed
Updated 10/16/2026
v0.5.0
dsh-image-router

Image Router

DeepSeek Harness plugin: analyse images out of band with a vision model — pasted images are digested into text before admission and a describe_image tool covers image paths, all without ever changing the session's model.

vision-media★ 0↓ 524✓ v0.5.0 scan passed
Updated 10/16/2026
v0.1.6
@allmodels/dsh-speech

Speech

Speech-to-text and spoken answer summaries for DeepSeek Harness using AllModels.io.

vision-media★ 3↓ 115✓ v0.1.6 scan passed
Updated 10/16/2026
v0.4.6
dsh-file-convert

File Convert

Local-first file conversion for DeepSeek Harness - images, PDF, data, audio/video and office documents. No API keys, no uploads, no token cost.

vision-mediaproductivity-workflow★ 3↓ 110
Updated 10/16/2026
v0.2.0
dsh-plugin-deepeye

Plugin Deepeye

DeepSeek Harness native plugin: vision capabilities for text-only LLMs (describe, OCR, VQA, layout analysis, clipboard)

vision-media★ 3↓ 108✓ v0.2.0 scan passed
Updated 10/16/2026
v0.3.0
dsh-live2d-avatar

Live2d Avatar

A switchable Live2D avatar stage and desktop companion for DeepSeek Harness.

ui-customizationvision-media★ 0↓ 425
Updated 10/16/2026
v1.1.8
dsh-client-ui-wallpaper

Client Ui Wallpaper

Use local images/videos (Dynamic Wallpaper.app assets) as wallpapers for the DSH desktop client: fill the window, background blur, independent panel/left and right sidebar opacity, automatic light/dark text, video thumbnails, rotation, and playlist synchronization. · Use local images or videos as th

ui-customizationvision-media★ 1↓ 186✓ v1.1.8 scan passed
Updated 10/16/2026
v0.4.1
@a9i5k4/dsh-ark9canvas

Ark9canvas

DSH image generation plugin Ark9canvas: Agent image generation (user approval required by default) + floating image generation workbench (aspect ratio/transparent background/batch/prompt library/multiple channels/generation history), supporting text-to-image/image-to-image via OpenAI-compatible imag

vision-mediaui-customization↓ 347✓ v0.4.1 scan passed
Updated 10/16/2026
v1.7.5
@loyalchiiina/dsh-chat-image-lightbox

Chat Image Lightbox

Chat images deserve a proper look: click once to open a full-screen lightbox (zoom, drag to pan, download/save, previous/next); turn all images in a conversation into a thumbnail grid with an adjustable number of columns, or hide them all at once without leaving blank space; local TIFF/HEIC images a

vision-mediaui-customization★ 2↓ 114✓ v1.7.5 scan passed
Updated 10/16/2026
v0.1.3
dsh-vision-guard

Vision Guard

Transparent image guard + vision analysis for DeepSeek Harness: text-only models read pasted images without the 400 session deadlock.

vision-media★ 0↓ 334✓ v0.1.3 scan passed
Updated 10/16/2026
← Previous12345…21Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in