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 13

CATEGORY

Vision & Media DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1042Memory & Context1300Coding & Developer Tools2786UI & Customization3656Integrations & Communication1910Vision & Media615Search & Research865Security & Access1268Models & Usage1682Productivity & Workflow2234

All plugins

614 plugins
v0.5.2
dsh-voice-scribe

Voice Scribe

Voice input plugin for DSH: tap or hold Alt to talk, then release or tap again to convert speech to text. Supports a hotword replacement list (hot.txt), custom polishing prompts, and a recording level indicator. Uses local offline recognition by default (SenseVoice; zero configuration, zero key, and

vision-media★ 0↓ 0
Updated 10/11/2026
Zv0.1.0
dsh-zimage-gen

Zimage Gen

DeepSeek Harness tool plugin: generate images with Alibaba Cloud Bailian Z-Image-Turbo (zimage_generate), and track usage counts and costs locally (zimage_quota).

vision-mediamodels-usage★ 0↓ 0
Updated 10/11/2026
Cv0.2.0
dsh-creative-plugin

Creative Plugin

DSH creative mode plugin: registers a creative_generate_image tool that bridges DeepSeek Harness sessions to any OpenAI-compatible text-to-image endpoint (default: StepFun step-image-edit-2).

vision-mediaintegrations-communication★ 0↓ 0
Updated 10/11/2026
v1.0.2
dsh-image-gen-plugin

Image Gen Plugin

Image generation tool and settings page for DeepSeek Harness, talking to any OpenAI-compatible /images/generations endpoint.

vision-media★ 0↓ 0
Updated 10/11/2026
Vv0.2.0
dsh-video-transcribe

Video Transcribe

DeepSeek Harness plugin: Paste a video link to download the audio track with a local toolchain and transcribe it offline (yt-dlp + ffmpeg + sherpa-onnx/SenseVoice), with automatic chunking for long audio and no cloud APIs.

vision-media★ 0↓ 0
Updated 10/11/2026
Yv0.2.0
dsh-youtube-study-notes

Youtube Study Notes

Turn a YouTube link into study notes: pulls the video's own captions, optionally reads on-screen content with a vision model, then asks for your own notes and merges everything into one document.

productivity-workflowvision-mediasearch-research★ 0↓ 0
Updated 10/10/2026
v0.1.6
dsh-image-tiler

Image Tiler

Shows oversized images to the model at a readably high resolution by tiling them before admission.

vision-media★ 0↓ 0
Updated 10/10/2026
Ev0.2.0
explainer-video-from-coursework

Explainer Video From Coursework

Turn a directory of structured coursework notes into a narrated, animated explainer-video series.

vision-media★ 0↓ 0
Updated 10/10/2026
Av0.1.0
dsh-auto-visual

Auto Visual

Plans original images for documents, sites and slides, generates them with a mock or OpenAI-compatible provider, and records each asset's declared usage

vision-mediaproductivity-workflow★ 0↓ 0
Updated 10/10/2026
Sv0.4.8
dsh-search-picture

Search Picture

DSH picture search: Bing/Baidu/360/Bilibili/Safebooru sources with Zhihu/Bilibili preference, stage candidates in a preview area, then write only the user-approved ones flat into the system Pictures album

search-researchvision-media★ 0↓ 0
Updated 10/10/2026
Pv1.0.0
dsh-plugin-hunyuan-image

Plugin Hunyuan Image

DSH native plugin: integrates Tencent Hunyuan Image Generation (Hy-Image-3.5-preview / Hy-Image-3.0), with a local image library, context awareness, and cross-platform portability.

vision-media★ 0↓ 0
Updated 10/10/2026
Uv1.0.0
dsh-ujn-image

Ujn Image

济大词元 text-to-image / image editing: Enter the API Key for the 济南大学大模型平台 on the DSH settings page to let DSH use the on-campus Qwen-Image model to generate and edit images.

vision-mediamodels-usage★ 0↓ 0
Updated 10/10/2026
v1.0.1
dsh-boot-video

Boot Video

Add a video startup intro to DeepSeek Harness (DSH): includes an mp4, lets you import your own videos (codecs the browser cannot decode are automatically converted to H.264), name them, and switch between them at any time; fades into the interface when playback ends, with click or Esc to skip; every

vision-mediaui-customization★ 0↓ 0
Updated 10/10/2026
Gv0.1.0
godot-imagegen

Godot Imagegen

Local AI art generation for DeepSeek Harness game development: drives the machine's SD WebUI / ComfyUI backends through eight image_* model tools, a /gig REST surface and a 美术工坊 (Art Studio) better-sidebar panel, writing Godot-ready assets.

vision-mediadeveloper-tools★ 0↓ 0
Updated 10/10/2026
Ov0.2.0
dsh-openrouter-voice

Openrouter Voice

Self-contained OpenRouter voice transcription for DeepSeek Harness: its own microphone control, its own host transport, its own OpenRouter model picker

vision-media★ 0↓ 0
Updated 10/10/2026
Av0.1.0
dsh-agnes-image

Agnes Image

DeepSeek Harness 生图插件：文生图 / 图生图 / 多图合成，基于 Agnes AI（agnes-image-2.5-flash）。零依赖，纯 JavaScript，无需构建。 | DSH image generation plugin for DeepSeek Harness: text-to-image, image-to-image, and multi-image composition via Agnes AI.

vision-media★ 0↓ 0
Updated 10/9/2026
Iv0.1.0
dsh-image-count-guard

Image Count Guard

Recover a DSH visual-model session when an upstream gateway rejects a request for carrying too many images: offload the oldest image occurrences to text placeholders and retry the step.

vision-media★ 0↓ 0
Updated 10/9/2026
Iv0.2.0
dsh-image-once

Image Once

Inlines each image block only in the request where it first appears, then swaps it for the harness's own placeholder text on every later request. On by default for every provider; each provider can be switched off or limited to specific models from the plugin page.

vision-media★ 0↓ 0
Updated 10/9/2026
Sv0.1.0
dsh-screenshot-win

Screenshot Win

DSH screenshot plugin: a camera button in the chat input + an Agent-callable screenshot tool (selected area / specified window / entire screen). Screenshots go directly into the conversation and are saved to the workspace.

vision-media★ 0↓ 0
Updated 10/8/2026
v0.1.5
@nutshelllee/dsh-voice-mode-desktop

Voice Mode Desktop

Full-duplex voice mode for DeepSeek Harness 0.2 desktop: streaming ASR to draft, sentence read-aloud, barge-in, live captions, plus an in-app settings page. An unofficial compatibility fork of dsh-voice-mode 0.7.15.

vision-mediaui-customization★ 0↓ 0
Updated 10/8/2026
Vv0.2.1
dsh-volume-knob

Volume Knob

Read the newest turn aloud from the DSH composer: a speaker button in the composer tool row, left of the model selector, 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, press-and-hold the icon to pic

vision-media★ 0↓ 0
Updated 10/8/2026
Vv1.0.0
dsh-video-tool

Video Tool

Video editing toolset for DeepSeek Harness — trim, concat, audio, subtitles, transform, transcode and frame grabbing, powered by ffmpeg.

vision-media★ 0↓ 0
Updated 10/8/2026
Mv0.1.1
dsh-media-dock

Media Dock

Media panel for the DSH right sidebar: add Douyin/YouTube links, download locally with yt-dlp, convert to 16 kHz mono WAV with ffmpeg, transcribe with the official speechToText (SenseVoice), display subtitles in the panel, and summarize with Agent in one click.

vision-media★ 0↓ 0
Updated 10/8/2026
Sv0.1.0
dsh-share-card

Share Card

DeepSeek Harness conversation screenshot beautifier: Click “Share Card” below any reply to render the response as a polished PNG sharing image in one step. Adjust the gradient background, font, colors, corner radius, width, and watermark; choose between light and dark themes and 8 gradient presets.

vision-mediaui-customization★ 0↓ 0
Updated 10/7/2026
Vv0.4.0
dsh-video-studio

Video Studio

DSH Video Workbench: image-text storyboarding, frontend code generation and editing, local MP4 export

vision-mediadeveloper-tools★ 0↓ 0
Updated 10/7/2026
Zv0.1.3
zhanshi

Zhanshi

DSH plugin: show generated images and videos inline in the conversation.

vision-media★ 0↓ 0
Updated 10/7/2026
Pv0.1.0
dsh-plugin-pdf-text

Plugin Pdf Text

Read text out of local PDF files inside DeepSeek Harness (DSH): one pdf_extract tool, page-by-page text, stats, scanned-PDF detection. Pure Node, no Python, no network.

productivity-workflowvision-media★ 0↓ 0
Updated 10/7/2026
Vv0.2.2
dsh-voice-ru

Voice Ru

Russian speech recognition for DSH voice input: local NVIDIA Nemotron 3.5 ASR 0.6B (GGUF) on transcribe.cpp, with model and runtime downloaded on first use.

vision-media★ 0↓ 0
Updated 10/6/2026
Iv0.1.0
@local/dsh-imagegen

Imagegen

OpenAI-compatible image generation and editing for DeepSeek Harness.

vision-media★ 0↓ 0
Updated 10/6/2026
Pv1.1.0
dsh-plugin-agnes-image

Plugin Agnes Image

Agnes image generation for DeepSeek Harness (dsh): an agnes_image tool plus a settings-page console

vision-media★ 0↓ 0
Updated 10/6/2026
← Previous1…1112131415…21Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in