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 & Media919Search & Research1.2kSecurity & Access1.8kModels & Usage2.4kProductivity & Workflow3.6k

All plugins

919 plugins
Vv0.1.0
dsh-vision-api-localorweb

Vision Api Localorweb

DSH plugin: Connects to image recognition model APIs (local large model image recognition tool + settings interface). Configure an OpenAI-compatible image recognition endpoint (LM Studio / vLLM / Ollama, etc.); leave the endpoint blank to disable the image recognition model.

↓ 0★ 1
Updated 8/21/2026
Dv1.0.0
deepseek-visual-plugin

Deepseek Visual Plugin

DeepSeek Harness visual understanding plugin: Converts images in user messages and tool results into textual descriptions for text-only task models (such as DeepSeek).

↓ 0★ 1
Updated 8/21/2026
Cv0.1.0
dsh-culture-movies

Culture Movies

Movie genre

↓ 0★ 1
Updated 8/21/2026
Wv1.3.0
@local/dsh-whisper-local

Whisper Local

Fully local multilingual speech recognition with whisper.cpp: 99 Whisper languages, automatic detection by default, no data sent over the Internet.

↓ 0★ 0
Updated 11/4/2026
Dv1.1.2
delivery-video

Delivery Video

Turn a feature that actually runs into a trustworthy delivery demo video, or a defect into a traceable feedback video: real screen recordings, edge-tts narration, word-synced subtitles and a deterministic quality gate (ffmpeg-based, self-contained pipeline).

↓ 0★ 0
Updated 11/4/2026
Vv1.0.2
voicetranser

Voicetranser

Fully local push-to-talk voice input for macOS: hold a global hotkey, speak, release — transcription is pasted at your cursor. Local-first STT (Qwen3-ASR MLX / SenseVoice / mlx-whisper), zero external APIs. This package ships the agent skill that installs, configures and troubleshoots the tool.

↓ 0★ 0
Updated 11/4/2026
Pv0.2.2
dsh-pf-stream

Pf Stream

DeepSeek Harness video perception plugin: adaptive dual-scale streaming sampling plus deterministic inspection, aligned to the DeepSeek-V4.1-Flash vision pipeline (42px superpixel grid, <=1024 tokens per image).

↓ 0★ 0
Updated 11/4/2026
Cv0.2.0
dsh-chat-share-image

Chat Share Image

Copy one finished assistant reply as a long PNG screenshot — tables re-laid out, referenced images full-size, overlong replies split into readable parts.

↓ 0★ 0
Updated 11/4/2026
Mv0.1.2
dsh-media-reader

Media Reader

Read local images, audio and video from DeepSeek Harness, including on text-only routes; includes a composer drag-and-drop target.

↓ 0★ 0
Updated 11/4/2026
Qv0.1.2
dsh-quicktime-player

Quicktime Player

Sidebar video player for DeepSeek Harness: streaming playback with seek, wheel zoom, drag pan and a custom control bar

↓ 0★ 0
Updated 11/4/2026
v1.1.1
dsh-cost-voice

Cost Voice

At the end of each session turn, announces the turn's cost using Alipay or Dabaifan voices; the amount is taken from dsh-cost-meter when available, otherwise estimated based on the model's per-turn price. Per-turn spend voice announcements for DeepSeek Harness with Alipay or Dabaifan voice packs.

↓ 0★ 0
Updated 11/4/2026
Iv0.1.6
dsh-image-viewer-pro

Image Viewer Pro

A proper image viewer for DeepSeek Harness: zoom, pan, rotate, download, copy, open with the default app, and gallery browsing for images inside the chat.

↓ 0★ 0
Updated 11/4/2026
Uv1.1.0
dsh-ug-viewer

Ug Viewer

Preview UG/NX models inside DSH: orbit with the mouse, pick faces/edges/features, and ask an AI about the selected geometry.

↓ 0★ 0
Updated 11/4/2026
v0.1.2
@deepwhale-cn/dsh-pdf-kit

Pdf Kit

Merge / split / compress PDFs / add watermarks / extract text and images

↓ 0★ 0
Updated 11/4/2026
Wv0.4.2
dsh-whale-tts

Whale Tts

Provider-agnostic text-to-speech tools for DeepSeek Harness agents: local audio files, voice profiles, and a settings card.

↓ 0★ 0
Updated 11/4/2026
Bv1.2.0
dsh-background-plugin

Background Plugin

Background image with adjustable opacity, fit, blur and dim for the DeepSeek Harness Web UI.

↓ 0★ 0
Updated 11/4/2026
Vv0.6.9
dsh-voice-chat-mode

Voice Chat Mode

Voice chat mode for DeepSeek Harness: always-on VAD listening, local speech-to-text, auto submit, and Edge TTS / system read-aloud.

↓ 0★ 0
Updated 11/4/2026
Dv0.1.5
dsh-doubao-video

Doubao Video

豆包视频工坊: Turn the 《大肥鱼豆包制作视频》SOP into machine-checkable gates — style locking / 12 storyboard fields / separate character cards and reference images / first-and-last-frame continuity / automatic voiceover and subtitle stitching

↓ 0★ 0
Updated 11/4/2026
Pv0.2.0
dsh-plugin-prompt-forge

Plugin Prompt Forge

Turn “I want this effect” into reproducible prompts. Reverse-engineer AI creations across five categories: images / videos / copywriting / web code / music.

↓ 0★ 0
Updated 11/4/2026
Cv0.1.0
dsh-cat-star

Cat Star

喵星大道 — cat beauty scoring for the DSH Web GUI: upload a cat photo or video, let AI auto-detect the breed, and get a CFA-inspired scorecard with radar chart, per-dimension commentary, a China-market price estimate, a share card, and an optional public leaderboard.

↓ 0★ 0
Updated 11/4/2026
v1.2.0
dsh-media-converter

Media Converter

Local media toolbox for DeepSeek Harness: convert, trim, split tracks, export subtitles, compress images, edit metadata, and Base64 — all through local ffmpeg.

↓ 0★ 0
Updated 11/4/2026
Qv1.2.0
dsh-qq-screenshot

Qq Screenshot

QQ-style screenshot for the DeepSeek Harness Web UI: Ctrl+Alt+A, drag a region, annotate, copy to the clipboard.

↓ 0★ 0
Updated 11/4/2026
Sv0.4.0
dsh-speech-to-text-gigaam

Speech To Text Gigaam

Local GigaAM (Sber) Russian speech recognition provider for DeepSeek Harness voice input

↓ 0★ 0
Updated 11/4/2026
Av0.2.0
@local/ai-voice

Ai Voice

AI voice studio for DeepSeek Harness: 9 local TTS engines (VoxCPM2 voice design, IndexTTS-2.5 emotion performance, Qwen3-TTS custom voice/clone, plus Spark-TTS / CosyVoice3 / OpenAudio S1-mini / GPT-SoVITS / F5-TTS / Kokoro), reference library and export.

↓ 0★ 0
Updated 11/4/2026
v0.1.4
dsh-mp4

Mp4

Preview MP4, M4V and MOV videos in the DSH right sidebar: a native video player replaces the “this file type cannot be previewed” placeholder.

↓ 0★ 0
Updated 11/4/2026
Iv0.2.0
dsh-image-editor

Image Editor

Separate image layers through Shenhuo MCP, edit in the default browser, and export PSD files in DeepSeek Harness.

↓ 0★ 0
Updated 11/3/2026
Pv2.4.0
publish-size-check

Publish Size Check

Publishing size check: Compare images against target platform specifications to see whether they can be posted and which parameter fails. Zero dependencies; checks geometric parameters only.

↓ 0★ 0
Updated 11/3/2026
Mv2.1.0
dsh-moss-image

Moss Image

Moss text-to-image plugin: Say what you want to draw in dsh and get an image, with an image library, art styles, and albums

↓ 0★ 0
Updated 11/3/2026
Vv0.3.5
dsh-video-learning

Video Learning

Video Deep Reading | Content restoration first: web video acquisition, 3-second baseline and change-triggered supplemental frames, 5-minute segmentation, high-definition PNGs, subtitles, and offline speech transcription

↓ 0★ 0
Updated 11/3/2026
Mv3.13.13
metaontic-video

Metaontic Video

AI video creation plugin for DeepSeek Harness: Seedance 2.0 long videos with multi-segment continuation, text-to-video, image-to-video, script and storyboard review, segment previews, resumable generation and local FFmpeg merging.

↓ 0★ 0
Updated 11/3/2026
← Previous1…1314151617…31Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in