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 & Media918Search & Research1.2kSecurity & Access1.8kModels & Usage2.5kProductivity & Workflow3.6k

All plugins

916 plugins
Ov1.4.2
dsh-op-splash

Op Splash

DeepSeek Harness splash animation plugin: plays a full-screen animation on cold start. The repository includes no media; import your own videos, images, or slideshows after installation.

↓ 0★ 1
Updated 10/27/2026
Mv0.3.0
dsh-minimax-multimodal

Minimax Multimodal

MiniMax web search, image understanding, image generation, speech synthesis and transcription for DeepSeek Harness

↓ 0★ 1
Updated 10/27/2026
Mv1.8.4
dsh-media-downloader

Media Downloader

Multi-site media downloader for DSH: Bilibili, Douyin and Xiaohongshu via native parsers, other sites via yt-dlp

↓ 0★ 1
Updated 10/27/2026
Mv1.32.0
mimo-voice-report

Mimo Voice Report

DeepSeek Harness plugin: speak a short completion notice and a two-sentence summary through Xiaomi MiMo TTS, with a popup portrait and a speech bubble that reveals text in step with the audio.

↓ 0★ 1
Updated 10/26/2026
Lv1.6.3
dsh-live2d-voice

Live2d Voice

Live2D session view with realtime voice: continuous voice input, streaming TTS, subtitle translation, multi-model catalog, standalone entry / Live2D 实时语音会话视图：连续语音输入、流式 TTS、字幕翻译、多模型目录、独立入口

↓ 0★ 1
Updated 10/26/2026
Pv1.1.1
dsh-plugin-agnes-image

Plugin Agnes Image

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

↓ 0★ 1
Updated 10/24/2026
Vv0.1.0
@local/vista-visual-harness

Vista Visual Harness

VISTA visual harness: lossless visual memory, model-directed inspect, exact pixel readout, notes and one-action-per-turn play for interactive desktop worlds.

↓ 0★ 1
Updated 10/24/2026
Bv1.7.2
dsh-boo550wt-animation

Boo550wt Animation

Customizable boot animation for DeepSeek Harness: upload your own video, picture or HTML page, play one of five built-in mini games, or watch either Wandering Earth 3D walkthrough (planetary engines, or the full 100 km → 100,000 ly voyage with its telemetry consoles and a recorded score) — and previ

↓ 0★ 1
Updated 10/24/2026
Sv0.2.0
dsh-siri-voice

Siri Voice

Siri-style running-light visualizer for the DeepSeek Harness (dsh) composer, plus rule-based cleanup of dictated transcripts (fillers, repeats, pause periods).

↓ 0★ 1
Updated 10/24/2026
Lv0.2.0
dsh-local-tts

Local Tts

DSH local reading: read conversations aloud. Choose one of two engines: local Style-Bert-VITS2 (supports custom/ cloned voices) or Microsoft edge-tts (natural Chinese).

↓ 0★ 1
Updated 10/23/2026
Gv0.1.5
dsh-grok-image

Grok Image

DeepSeek Harness plugin: Grok Imagine image generation as a model tool (subscription)

↓ 0★ 1
Updated 10/20/2026
Vv0.1.7
@xiciyang/dsh-visual-memory

Visual Memory

Lossless visual memory for DSH agents: verbatim content-addressed image storage, an explicit-attention ledger, labelled comparison sheets, and exact pixel reads — no second vision model in the loop.

↓ 0
Updated 10/19/2026
Vv0.4.0
dsh-video-bg

Video Bg

Play a local video as the DeepSeek Harness Web/Desktop chat background, with play/pause, opacity and scrim controls.

↓ 0★ 1
Updated 10/19/2026
Ov0.6.3
dsh-ollama-vision-bridge

Ollama Vision Bridge

DSH (>= 0.2.0-rc.1) vision bridge: when the selected chat model is text-only, attached images are described by a local Ollama VL model (default qwen3-vl:8b) with keep_alive VRAM cooling. npx CLI (setup/model/status/check) + install-time patch of dsh-api-session-controller prompt admission + runtime

↓ 0★ 1
Updated 10/19/2026
v0.5.0
kkj-luna-dsh-image-bridge

Kkj Luna Dsh Image Bridge

生图桥: Connect models without image generation/editing capabilities to external image generation models. Configure the API and key in the Web interface, and the model can directly call image generation and editing capabilities.

↓ 0★ 1
Updated 10/19/2026
Vv0.1.6
dsh-visual-memory

Visual Memoryalt · xiciyang

Lossless visual memory for DSH agents: verbatim content-addressed image storage, an explicit-attention ledger, labelled comparison sheets, and exact pixel reads — no second vision model in the loop.

↓ 0
Updated 10/19/2026
Lv0.1.1
@ycp424c/dsh-luna-vision-bridge

Luna Vision Bridge

DSH LLM adapter that transcribes native image attachments with Codex Luna before delegating to DeepSeek

↓ 0★ 1
Updated 10/19/2026
Vv0.2.2
dsh-visual-explainer

Visual Explainer

DeepSeek Harness plugin: explain professional/technical terms first (visual_terms), then render visual explanation cards as PNG (visual_explain) or a clickable offline mermaid page (visual_interactive)

↓ 0★ 1
Updated 10/18/2026
Tv0.3.1
taxue-dsh-artisan

Taxue Dsh Artisan

taxue artist: reverse-engineers image/video prompts, extracts deterministic color palettes, audits and optimizes prompts, and generates images through multiple providers (with optional image control), while bridging taxue-imagegen’s template slot filling and output acceptance.

↓ 0★ 1
Updated 10/16/2026
Av0.2.0
dsh-auto-image

Auto Image

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.

↓ 0★ 1
Updated 10/15/2026
Iv0.2.0
dsh-image-tool

Image Tool

DeepSeek Harness image generation and editing tool plugin: connects any OpenAI-compatible image generation/editing service as a platform tool, allowing models to generate or modify images directly in conversations. Images are output as native platform image blocks and displayed in the tool card (thu

↓ 0★ 1
Updated 10/14/2026
Vv0.3.13
dsh-voice-mini

Voice Mini

Voice-feedback plugin for DeepSeek Harness: a speak tool, readReplies narration, an LLM verbalizer pass, per-session voices, chimes, a monitoring panel, and a native macOS floating pet. zh/en i18n.

↓ 0★ 1
Updated 10/13/2026
Nv0.2.0
dsh-neon-splash-v3

Neon Splash V3

DSH desktop opening animation: pure black opening, progressive deblurring and brightening, automated terminal startup and workspace model connection, plugin preloading, login interface, AI voice greeting, AR HUD compilation sequence, and code-filled transition into the main interface.

↓ 0★ 1
Updated 10/12/2026
Sv1.1.1
dsh-screenshot-xn

Screenshot Xn

DSH Screenshot (xn): Full-screen WeChat-style region selection and annotation (rectangle/ellipse/arrow/brush/mosaic/text, with undo/redo), with one-click insertion into chat, copying, or saving as; selected regions can be OCR-recognized and translated (offline recognition + reuse of models already c

↓ 0★ 1
Updated 10/11/2026
Vv0.3.0-rc.7
@local/dsh-video-wallpaper

Video Wallpaper

Local image and looping-video wallpapers for the DeepSeek Harness Desktop and Web UI

↓ 0★ 1
Updated 10/11/2026
Lv1.1.0
dsh-local-ocr

Local Ocr

Offline OCR tool for DeepSeek Harness: registers an ocr tool that runs the bundled ocr_tool.py (Windows native OCR, then RapidOCR, then Tesseract) over images and PDFs.

↓ 0★ 1
Updated 10/11/2026
Mv0.1.5
dsh-multi-tts

Multi Tts

Text-to-speech (MiniMax / OpenAI-compatible TTS, selectable provider and voice)—a read-aloud button beside each reply, an auto-read toggle for the input box, and provider and voice selection in the settings page. Zero build, pure JS.

↓ 0★ 1
Updated 10/11/2026
Iv0.1.1
@dsh-plugin/dsh-image-annotate

Image Annotate

An annotation pen for the DeepSeek Harness image lightbox: draw, label, then move / resize / re-edit any mark, and send the annotated PNG straight into the composer. 给 DSH 图片预览加一支画笔。

↓ 0★ 1
Updated 10/10/2026
Vv0.3.0
dsh-v4flash-tiler

V4flash Tiler

DSH plugin: auto-tiles oversized chat images into labelled grid pieces (row/col metadata, overlap-aware, multi-image group isolation) so the DeepSeek vision model keeps fine detail instead of the ~800px downsample.

↓ 0★ 1
Updated 10/8/2026
Vv0.1.0
dsh-voice-ptt

Voice Ptt

Push-to-talk dictation for DeepSeek Harness: hold a single key in the composer, release, and the transcript is inserted into your draft.

↓ 0★ 1
Updated 10/7/2026
← Previous1…1011121314…31Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in