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
Tv0.5.1
dsh-tool-describe-image

Tool Describe Image

DSH plugin: image understanding via any OpenAI-compatible vision API, paste-to-describe, and an animated whale-buddy desktop pet with status bubbles and a floating settings panel

↓ 0★ 4
Updated 8/25/2026
Vv0.2.3
dsh-vision-tiler

Vision Tiler

Loss-aware, full-coverage image tiling for DeepSeek Harness vision models

↓ 0★ 4
Updated 8/23/2026
Mv0.2.1
dsh-medomni

Medomni

Medical imaging specialist tools for deepseek-harness: MAIRA-2 and MedGemma report generation for chest X-ray/CT/MRI/retinal (fundus) images, TotalSegmentator organ segmentation, BiomedCLIP zero-shot ultrasound classification, and BiomedParse text-prompted segmentation across X-ray, CT, MRI, ultraso

↓ 0★ 4
Updated 8/22/2026
Iv0.2.0
dsh-image-subagent

Image Subagent

Allow text-only primary models (DeepSeek V4, etc.) to receive image attachments: remove the modality declaration from the text-only route to pass the 0.1.1 admission gate, project images into placeholder text carrying the complete attachmentId, and have the primary model delegate reading to a visual

↓ 0★ 4
Updated 8/22/2026
Dv0.2.9
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 8/20/2026
Sv0.1.0
dsh-stt-input

Stt Input

Speech-to-text voice input for the DeepSeek Harness (DSH) web GUI: click the mic button in the composer to turn speech into text in the input box. Supports the browser's built-in Web Speech API (zero-config, Chrome/Edge) and OpenAI-compatible Whisper endpoints (OpenAI / Groq) with the STT model sele

↓ 0★ 4
Updated 8/20/2026
v0.3.0
@toddzheng024/vapor-voice-local

Vapor Local Voice

Optional macOS local reference-voice preparation for Vapor

↓ 3
Updated 11/4/2026
v0.3.0
@toddzheng024/vapor-review-gemini

vapor-review-gemini

Vapor review gemini tool operations

↓ 3
Updated 11/4/2026
Cv0.2.3
dsh-cet-vocab

Cet Vocab

Vocabulary memorization (CET-4/6): shell.overlay floating word cards that can be dragged, minimized, and resized; multiple-choice questions with three-button scoring and visually similar word distractors + Ebbinghaus spaced repetition; invoke anytime with shortcuts such as Alt+Q; online native US/UK

↓ 0★ 3
Updated 11/3/2026
Vv0.5.4
@orderg-x/dsh-video-preview

Video Preview

Inline video and audio playback for DeepSeek Harness: a play_video tool plus a native player under the reply and in the sidebar, served by a guarded, Range-capable streaming route, and a look_video tool that shows the model frame contact sheets with audio, black-frame and phone-compatibility checks.

↓ 0★ 3
Updated 11/1/2026
Wv0.1.1
wavespeed-dsh-skill

Wavespeed Dsh Skill

WaveSpeed skill for DeepSeek Harness (dsh): generate and edit AI media (image, video, audio, 3D) via the open-source wavespeed CLI.

↓ 0★ 3
Updated 11/1/2026
Qv0.1.2
dsh-qwen-paint

Qwen Paint

【(绘图)千问 · @奇迹与你】Lets DeepSeek Harness directly call the local ComfyUI (Qwen Qwen-Image model) to generate images in conversation: say “draw a cat” and an image is generated, saved to the 千问1生图 directory, and displayed directly in the chat. Uses only local 127.0.0.1, with no network access, no cost,

↓ 0★ 3
Updated 10/8/2026
Av3.0.0
@yankafei/ascii-h3-director

Ascii H3 Director

Direct ASCII art and kinetic-typography films with MiniMax H3 — deterministic zero-dependency preview engine, motion-grammar chain planning, seam-checked continuation, and a Director Console for DeepSeek Harness.

↓ 0★ 3
Updated 10/7/2026
Mv0.4.0
@baconbao/dsh-mermaid-image-preview

Mermaid Image Preview

A DeepSeek Harness Plugin for Previewing Mermaid Diagram by Images in Chat Sessions. View on GitHub (https://github.com/baconbao/dsh-mermaid-image-preview).

↓ 0★ 3
Updated 10/3/2026
v0.2.1
dsh-wx-skin

Wx Skin

DSH Web GUI skin plugin: a sidebar “Skins” panel that supports user-selected local images / URLs / local folder slideshows (sequential or random, without repeats within a cycle) as full-screen backgrounds, with presets, darkening, blur, and skin disabling. Settings persist across refreshes (external

↓ 0★ 3
Updated 9/27/2026
Vv0.2.2
voco-input-sh

Voco Input Sh

VocoType voice input bridge for DSH Web: mic button + recording panel in the composer, auto-insert recognized text (dedupe, auto-launch/deploy, mtime-optimized polling)

↓ 0★ 3
Updated 9/13/2026
Iv2.9.2
@xiaoyuink/dsh-image-vision

Image Vision

Image recognition plugin: Automatically detects whether the current model has vision capabilities. If so, it uses the current model with the plugin’s preset prompts for analysis; otherwise, it calls the vision model configured in the plugin. Text models can paste, upload, or drag images directly int

↓ 0★ 3
Updated 9/4/2026
Vv0.3.11
dsh-voco

Voco

DSH plugin dsh-voco

↓ 0★ 3
Updated 8/31/2026
Vv1.2.0
dsh-visibridge

Visibridge

Host-level vision bridge for text-only models: analyze_image tool (Ollama local / Xiaomi MiMo cloud / any OpenAI-compatible endpoint) returning structured evidence.

↓ 0★ 3
Updated 8/23/2026
Vv0.1.0
dsh-vision

Vision

Local vision bridge for DeepSeek Harness

↓ 0★ 3
Updated 8/22/2026
Pv0.2.0
dsh-plugin-video-player

Plugin Video Player

DSH web GUI client plugin: video browsing window (select folder / Douyin-style vertical video browsing / ←→ seek / ↑↓ or drag to switch)

↓ 0★ 3
Updated 8/21/2026
Vv1.3.0
dsh-vision-imagen

Vision Imagen

DeepSeek Harness 全能插件：识别/生图/改图一体化，无需切换模型——用常规 DeepSeek 模型即可自动调用视觉与生图模型（gemini_vision / gemini_generate_image / gemini_optimize_image）。多后端：Gemini 原生 + 任意 OpenAI 兼容服务（GPT-4o、Qwen-VL、GLM-4V、Moonshot、gpt-image、DALL-E、Flux、Stable Diffusion、OpenRouter、硅基流动、各类中转等），生成后自动视觉自检反馈，优于 modlens。

↓ 0★ 3
Updated 8/21/2026
Mv0.1.0
meow-vision

Meow Vision

dsh plugin: gives text models a pair of eyes + gives multimodal models a pair of eyes to observe UI rendering — settings popup for selecting a vision model + meow_vision tool + meow_preview component screenshot tool

↓ 0★ 3
Updated 8/21/2026
Fv0.3.5
dsh-film-analysis

Film Analysis

DSH Web UI plugin for film & audiovisual-language analysis: frame metrics, 8-dimension forms, auto shot detection with AI shot breakdowns, annotation, reports and shot lists. Bundled ffmpeg + offline Chinese OCR. UI: zh/English; analysis output in Simplified Chinese.

↓ 0★ 2
Updated 11/4/2026
Mv1.9.1
@tzyc/dsh-model-visibility

Model Visibility

Choose which models appear in the chat composer's model list, with per-provider groups, per-model capability tags sourced from the adapter, the relay model list, a built-in catalog, vendor corrections and manual overrides, separate coloured labels for image/video generation models, name search and c

↓ 0★ 2
Updated 11/4/2026
Lv0.1.0
dsh-live-vibecoding

Live Vibecoding

Let your DeepSeek Harness agent go live on Bilibili: reads the room, thanks gifts, welcomes viewers, remembers regulars, and talks with its own voice on a stage you can skin.

↓ 0★ 2
Updated 11/2/2026
Dv0.1.1
ds-tts

Ds Tts

Read conversations aloud in DSH using DeepSeek official voices, export audio, and provide APIs and tools for text-in/audio-out. The host uses DS official TTS (ticket + wss), while text submission is completed by a real browser via CDP (no reverse-engineering PoW or spoofing TLS fingerprints).

↓ 0★ 2
Updated 10/31/2026
Pv1.4.2
dsh-pet-luotianyi

Pet Luotianyi

Luo Tianyi desktop pet: a virtual singer living in DSH, draggable and interactive; dialogue supports preset and AI modes, with built-in token usage and cost statistics, image replacement, and AI automatic background removal (Fast/Standard/Precise modes) with preview fine-tuning.

↓ 0★ 2
Updated 10/30/2026
v0.4.0
@max-null/dsh-capture

Capture

SSiD (思灵) quick screenshot capture: tray/hotkey → fullscreen box-select overlay → cropped image into the current conversation composer

↓ 0★ 2
Updated 10/30/2026
Vv0.8.1
dsh-voice-dialog

Voice Dialog

Voice dialog for DeepSeek Harness: multi-speaker ASR, priority queuing, auto-read replies

↓ 0★ 2
Updated 10/29/2026
← Previous1…7891011…31Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in