DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

Plugins Presets Docs News

Community

Publish a plugin Contact Report an issue

Resources

Plugin Hub on GitHub DeepSeek Harness System status Privacy 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 plugins Agents & Orchestration1.5k Memory & Context2.1k Coding & Developer Tools3.9k UI & Customization5.6k Integrations & Communication3k Vision & Media910 Search & Research1.2k Security & Access1.8k Models & Usage2.4k Productivity & Workflow3.6k

All plugins

910 plugins

@deepseek-ai/dsh-experimental-voice-input-bundle

Experimental Voice Input Bundle

Experimental voice input with local SenseVoice; downloads its runtime on first use

🔥 ↓ 650.8k

Updated 11/4/2026✓ Scan passed

@liustack/modlens

Modlens

Plug-in vision for text-only LLMs, powered by the free Antigravity CLI

🔥 ↓ 120.3k★ 4.8k

Updated 11/4/2026✓ Scan passed

dsh-image-gen

Image Gen

Bring ChatGPT-like image generation to DeepSeek Harness — Gemini, OpenAI, Seedream, DashScope, local ComfyUI & more.

🔥 ↓ 23.9k★ 1.1k

Updated 11/4/2026✓ Scan passed

Ab Ocr

--- description: "The out-of-tree ocr tool: recognizes a scanned PDF or image page by page, merges the pages in order only after the last one, and saves one Markdown document with the heading levels the model decided." kind: "package-reference" ---

Updated 11/4/2026

@linxin666/dsh-tool-describe-image

Tool Describe Image

Model-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable —

↓ 2.4k★ 10.1k

Updated 11/4/2026✓ Scan passed

dsh-video-storyboard

Video Storyboard

Turn a video into storyboard images you can cite: one frame per shot, cell size follows cut density (1/1 … 1/8), row-packed into as few images as possible, with a timestamped index the model can quote and a tier map it can override.

🔥 ↓ 19.4k★ 426

Updated 11/4/2026✓ Scan passed

@anionex/dsh-vision-toolkit

Vision Toolkit

DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.

Updated 11/4/2026

See Now

Let DSH watch a live screen or camera feed: score every frame by how much the picture changed, keep only the ones that matter, and pack them into one image. · 让 AI 实时看见你的屏幕，只传「画面变了」的那几帧。

↓ 6.4k★ 308

Updated 11/4/2026✓ Scan passed

dsh-video-skin

Video Skin

DSH video skin: one short clip loops as the chat background across the entire interface (muted, adjustable opacity), while another provides a sound-enabled startup animation (crossfades into the interface at the end and can be skipped at any time by clicking the screen). Zero dependencies.

🔥 ↓ 18.7k★ 103

Updated 11/4/2026

@dickpy/dsh-imagegen

Imagegen

AI image generation plugin for the dsh web GUI: text-to-image and image-to-image through configurable provider channels (gpt-image-2 / grok-imagine-image / nanobanana series / seedream-5.0-pro / dall-e-3, with native xAI Grok Imagine, Google Nano Banana a

↓ 3.3k★ 167

Updated 11/4/2026✓ Scan passed

dsh-boot-suite

Boot Suite

Two-scene startup animation (default Archive Warm White + Whale Girl scanning and opening her eyes, switchable between 2K/4K), supporting video/image imports, three transitions, 11→6 voiceover voices and five sound effects, chat backgrounds/looping videos, a built-in iframe startup template (全景大肥鱼-含

Updated 11/4/2026

@q253595422/dsh-imagegen-video

Imagegen Video

AI image AND video generation plugin for the dsh web GUI, with a complete video pipeline alongside the image pipeline. Images: text-to-image and image-to-image through configurable provider channels (gpt-image-2 / grok-imagine-image / nanobanana series /

Updated 11/4/2026✓ Scan passed

dsh-game-material-master

Game Material Master

Game Materials Master: The DSH plugin includes seven official modules—eight-direction image generation, image generation, sprite-sheet generation, a 45° map editor, a top-down map editor, music generation and editing, and sound-effect generation—plus experimental skeletal animation generation. The c

↓ 1.5k★ 118

Updated 11/4/2026✓ Scan passed

dsh-video-lens

Video Lens

Give text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件（场景感知抽帧 + VLM + 可选语音转录）

Updated 11/4/2026

Codex

ChatGPT OAuth, Codex models, search, read_image URL support, and configurable GPT Image generation for DeepSeek Harness

Updated 11/4/2026

@dsh-external/dsh-vision-toolkit

Vision Toolkitalt · @dsh-external

DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.

Updated 11/4/2026✓ Scan passed

@goodandready/dsh-image-gen

Image Genalt · @goodandready

Image generation for DeepSeek Harness: a generate_image tool with pluggable providers — the FAL queue, any OpenAI-compatible images API, or a ChatGPT/Grok subscription with no API key at all. The picture is shown inline in the conversation; the model rece

Updated 11/4/2026

@goodandready/dsh-voice

Voice

Voice input for DeepSeek Harness: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, plus any OpenAI-compatible API of your own).

Updated 11/4/2026✓ Scan passed

picturereader

Picturereader

Unified image understanding plugin for DeepSeek Harness (DSH). Visual twin adapter for native thumbnails + auto-analysis on any text-only model (incl. pi-ai providers); privacy/smart/strict routing; local tools (scan/OCR×4 engines (windows/macos/paddle/ra

Updated 11/4/2026✓ Scan passed

Voicealt · STARDUSTLC666

DSH voice tool: Edge TTS text-to-speech, ASR-compatible transcription, workspace file protection, and concurrent output. Issues and PRs are welcome.

Updated 11/4/2026

dsh-mobile-use

Mobile Use

Put a real phone in the DSH right panel: interact directly with the live mirror, circle an area to annotate and send it back to the session, and let the model read the UI text tree without screenshots. Uses only the local loopback; no screen uploads.

Updated 11/4/2026✓ Scan passed

Speak

Make your AI harness speak — voice announcements for DSH and other AI coding harnesses (Windows SAPI5 + macOS system voices)

Updated 11/4/2026

dsh-video-understand

Video Understand

Low-cost video understanding tool: Bilibili links/BV/local videos → information layer (ASR + scenes + object trajectories + YOLO) → summaries + Q&A. Question-driven dynamic routing across levels (L0/L1/L2), semantic-layer reuse, and budget caps. Self-contained engine with no external dependencies.

Updated 11/4/2026✓ Scan passed

dsh-vision-router

Vision Router

Eyes for text-only DeepSeek Harness agents: built-in free vision chain + pixel-level tools. Remote vision providers, including the default free fallback, receive image content unless strict local-only use is configured.

🔥 ↓ 20.4k★ 0

Updated 11/4/2026

dsh-agnes-studio

Agnes Studio

🎬 泡泡猫的影视工具 — AI film and television creation workstation: text-to-image, image-to-image, text-to-video, image-to-video, short drama script breakdown, and prompt specialist. Supports six major providers: Agnes / DeepSeek / Qwen / 豆包 / MiniMax / Ollama. Global overlay stays out of the way of dialogs,

Updated 11/4/2026✓ Scan passed

dsh-design-qa

Design Qa

Let any text-only model in DeepSeek Harness read images. Image recognition is an on-demand tool—images do not enter the main model context, and you pay nothing if they are not viewed; includes an evaluation set with 23 defects for self-testing when switching models.

Updated 11/4/2026✓ Scan passed

dsh-mpkg-wallpaper

Mpkg Wallpaper

DSH Web Wallpaper Engine mpkg background plugin: directly parses .mpkg in the browser (preview.gif animated backgrounds, embedded mp4 videos, and time-based switching), with uniform full-screen blur, independent blur for dialogs/popups/overlays, camera zoom and pan, a clock, and conflict detection.

Updated 11/4/2026✓ Scan passed

dsh-plugin-startup-animation

Plugin Startup Animation

Animated full-screen startup screen shown while DeepSeek Harness boots — click to skip. Ships a built-in MP4/wallpaper/audio library and accepts your own files. 开机动画 / 启动动画：启动 Harness 时显示全屏动画，随包内置视频、壁纸与开机音频，也可以用自己的素材。

Updated 11/4/2026

Gsv Tts

DSH plugin for local GSV-TTS-Lite voice cloning + Edge cloud simple mode: voice presets, auto-read, engine setup assistant, read-aloud button, settings panel

Updated 11/4/2026✓ Scan passed

dsh-vision-proxy

Vision Proxy

DeepSeek brain + automatic image transcription for DeepSeek Harness: a deepseek-vision provider route that transcribes attached images to text via any OpenAI-compatible VLM before delegating to the text-only DeepSeek adapter. Paid fast path with a key (Da

Updated 11/4/2026

1 2 3…31 Next →

DeepSeek Harness Plugin Hub

Profiles Plugins Categories News Docs Sign in Manage Profiles

Profiles Plugins Categories News Docs Sign in