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

909 plugins
v0.2.6
@linenxi-ctrl/dsh-vision

Vision

Provides DeepSeek Harness with an add-on image recognition model: web configuration panel, automatic image recognition and response when images are sent, model-controlled screenshot recognition tool, multi-protocol support, and one-click installation/uninstallation.

↓ 0★ 9
Updated 11/4/2026
Tv0.1.0
teach-math-with-manim

Teach Math With Manim

Open-source companion repository for the book 《Manim，让数学看得见》: source code for 60+ educational animation examples + the manim-teaching AI Skill (including the DeepSeek Harness plugin)

↓ 0★ 9
Updated 8/31/2026
v0.3.0
@toddzheng024/vapor-editing

vapor-editing

Vapor editing tool operations

↓ 8
Updated 11/4/2026
Qv1.9.0
qiaomu-reader-dsh

Qiaomu Reader Dsh

乔木阅读: DSH's EPUB, PDF, TXT, Markdown, and HTML reader, supporting read-aloud, vocabulary notebook, reading notes, and a built-in AI reading companion.

↓ 0★ 8
Updated 11/3/2026
Hv0.3.2
dsh-highres-vision

Highres Vision

DeepSeek Harness vision enhancer: raises image limits to the official DeepSeek values, raises the per-model request image budget for DeepSeek-V4.1-Flash, and provides high-resolution tiled image reading via a dedicated tool.

↓ 0★ 8
Updated 9/11/2026
Vv0.2.6
@nn12138/dsh-voice

Voice

Voice input plugin for DeepSeek Harness: microphone → local/browser speech recognition → text submitted as a normal chat message (input-only, preset-agnostic)

↓ 0★ 8
Updated 8/21/2026
v0.3.0
@toddzheng024/vapor-motion-viggle

vapor-motion-viggle

Vapor motion viggle tool operations

↓ 7
Updated 11/4/2026
v0.3.0
@toddzheng024/vapor-images

vapor-images

Vapor images tool operations

↓ 7
Updated 11/4/2026
Bv0.4.3
dsh-bili-watch

Bili Watch

Read B站 videos as text for AI: metadata, comments, danmaku, subtitles, local ASR transcription, and frame-extracted OCR; supports b23.tv short links and av numbers, with a configurable frame cache directory. Runs locally without uploading, with content consistency checks, instant repeat reads, and A

↓ 0★ 7
Updated 11/1/2026
Ov0.2.0-beta.1
dsh-omni-workstation

Omni Workstation

Omni-modal workstation plugin for DeepSeek Harness: analyze_image + 6 vision toolkit tools (zoom/sample_colors/image_diff/ocr/detect/show), generate_image, and generate_video (t2v/i2v async-task). Backed by an ordered multi-card list (OpenAI/Anthropic/Gemini protocols; Custom/Ollama plus 28 built-in

↓ 0★ 7
Updated 11/1/2026
Gv0.3.3
dsh-gpt-sovits

Gpt Sovits

GPT-SoVITS text-to-speech for the DeepSeek Harness web GUI: per-reply read-aloud, an auto-read toggle, native model switching, a settings page, and a startup memory gate that keeps the engine from starting when RAM is short. Ships no model weights and no reference audio.

↓ 0★ 7
Updated 10/21/2026
v0.3.0
@toddzheng024/vapor-review

vapor-review

Vapor review tool operations

↓ 6
Updated 11/4/2026
v0.3.0
@toddzheng024/vapor-captions

vapor-captions

Vapor captions tool operations

↓ 6
Updated 11/4/2026
Pv0.4.4
dsh-pdf-translator

Pdf Translator

AI vision PDF translation and LaTeX reconstruction for DeepSeek Harness

↓ 0★ 6
Updated 10/31/2026
Qv2.19.0
dsh-qwen-studio

Qwen Studio

Qwen Image 2.1 for DeepSeek Harness: native reference editing on Apple Silicon MLX and self-hosted CUDA, LoRA, ControlNet, inpainting and live chat progress

↓ 0★ 6
Updated 10/21/2026
v0.3.0
@toddzheng024/vapor-music

vapor-music

Vapor music tool operations

↓ 5
Updated 11/4/2026
Vv2.0.0
dsh-video-coursemap

Video Coursemap

Video Course Knowledge Map Agent 2.0: Periodically monitors the browser’s foreground window to detect Bilibili video courses in real time, automatically classifies subjects by keywords, retrieves video descriptions, subtitles, danmu, and comments for knowledge summaries, and outputs a Word knowledge

↓ 0★ 5
Updated 11/3/2026
v0.3.0
dsh-plugin-control-your-capture

Plugin Control Your Capture

Add capture tools to DSH: capture_screenshot captures a monitor, window, or region in physical pixels and returns the image directly to the model; capture_recording records a monitor or physical-pixel region as MP4 in a Windows single-screen console; never upscale.

↓ 0★ 5
Updated 10/30/2026
Iv0.6.5
@alger-ai/dsh-image-preview

Image Preview

Image preview in the dsh session: read_image, user-sent, assistant/Markdown/present images, and a full-size lightbox with zoom, rotate, pan, download, file actions, and cross-image navigation

↓ 0★ 5
Updated 10/18/2026
v1.2.0
@paicat1/dsh-screenshot

Screenshot

Standalone screen capture for DeepSeek Harness (dsh): browser hotkeys plus an agent-facing capture+read tool. Forked out of @liustack/modlens#48 (upstream declined the feature).

↓ 0★ 5
Updated 9/8/2026
Iv1.0.0
dsh-inline-media-viewer

Inline Media Viewer

Persistent inline image, video, and audio previews for DeepSeek Harness Web conversations, with workspace-confined local reads and a configurable ComfyUI proxy.

↓ 0★ 5
Updated 8/28/2026
Tv0.1.2
dsh-tool-see-image

Tool See Image

see_image tool for DSH: route image files to a configurable vision model (OpenAI-compatible API) and relay its description back to a text-only model

↓ 0★ 5
Updated 8/27/2026
v0.3.0
@toddzheng024/vapor-audio

vapor-audio

Vapor audio tool operations

↓ 4
Updated 11/4/2026
Pv1.4.0
dsh-pet-voice-fishy

Pet Voice Fishy

大肥鱼语音: Makes DSH desktop pets speak through speech bubbles. Local offline 鱼鱼酱 / 鱼鱼姐 voices (no Key required, works without an internet connection, 1.25x speed) + 8 offline Kokoro Chinese female voices.

↓ 0★ 4
Updated 11/4/2026
Tv0.1.0
dsh-tts-bridge-wechatagent-bridge

Tts Bridge Wechatagent Bridge

Record the voice spoken by 朗读桥 as SILK and send it to the current WeChat chat via a native WeChat voice message.

↓ 0★ 4
Updated 10/28/2026
Vv0.8.2
@haoku123/dsh-voice

Voicealt · @haoku123

Full-duplex voice mode for DeepSeek Harness: streamed ASR -> LLM -> TTS with barge-in

↓ 0★ 4
Updated 10/23/2026
Vv1.0.0
dsh-voice-polish

Voice Polish

「声琢」VoxPolish — 把说出来的话打磨成清晰表达：原话/整理后双通道，先说后改再发送，全程不碰输入框。Voice input with an expression coach for DeepSeek Harness; local SenseVoice ASR, no extra model download.

↓ 0★ 4
Updated 10/14/2026
Rv0.4.0
@f1star/dsh-research

Research

A DeepSeek Harness research workspace with archived PDF reading, optional OCR, human review, cited reports, and recoverable research tasks.

↓ 0★ 4
Updated 9/8/2026
Pv0.1.2
dsh-paddleocr-skills

Paddleocr Skills

PaddleOCR text-recognition and document-parsing skills with native DeepSeek Harness tools and GUI configuration.

↓ 0★ 4
Updated 9/2/2026
Dv0.3.0
@limccn/deepseek-vl-support

Deepseek Vl Support

Give DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.

↓ 0★ 4
Updated 9/1/2026
← Previous1…678910…31Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in