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.

Vision & Media DSH plugins

CATEGORY

Vision & Media DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1027Memory & Context1285Coding & Developer Tools2772UI & Customization3636Integrations & Communication1887Vision & Media613Search & Research848Security & Access1263Models & Usage1664Productivity & Workflow2212

All plugins

614 plugins
v3.27.1
@liustack/modlens

Modlens

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

vision-media★ 4275🔥 ↓ 27.2k✓ v3.27.1 scan passed
Updated 10/16/2026
v0.3.24
@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 —

vision-media★ 8813↓ 2.5k✓ v0.3.24 scan passed
Updated 10/16/2026
v0.1.46
@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.

vision-mediadeveloper-tools★ 896↓ 2.9k
Updated 10/16/2026
v0.1.0
deepseek-ivideo

Deepseek Ivideo

iPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.

vision-media★ 7001↓ 302
Updated 10/16/2026
v1.6.9
@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

vision-media★ 116↓ 2.8k
Updated 10/16/2026
v0.1.7-alpha.1
@deepseek-ai/dsh-experimental-voice-input-bundle

Experimental Voice Input Bundle

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

vision-media★ 0🔥 ↓ 279.8k✓ v0.1.7-alpha.1 scan passed
Updated 10/16/2026
v0.3.2
dsh-codex

Codex

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

developer-toolsvision-media★ 70↓ 618
Updated 10/16/2026
v0.1.4
@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.

vision-mediaui-customization★ 896↓ 46✓ v0.1.4 scan passed
Updated 10/16/2026
Gv0.6.0
dsh-game-material-master

Game Material Master

Game Asset Master: a DSH plugin with three official modules—eight-direction image generation, image generation, and sprite-sheet generation—as well as experimental modules for 45° map tile generation, skeletal animation generation, and a map editor (a remake based on AsLib’s RPG Map Maker: single-sc

vision-mediaui-customization★ 52↓ 772
Updated 10/16/2026
v0.7.24
dsh-voice-mode

Voice Mode

Full-duplex voice plugin for DeepSeek Harness: local zipformer2 streaming ASR (no API key) → editable draft; Edge TTS or local VITS / Kokoro read-aloud with live captions; true barge-in; hardened HTTP surface + model SHA256 pinning; compatible with all ds

vision-media★ 17↓ 1.2k✓ v0.7.24 scan passed
Updated 10/16/2026
v0.1.4
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.

vision-media★ 44↓ 483✓ v0.1.4 scan passed
Updated 10/16/2026
v0.12.2
@goodandready/dsh-image-gen

Image Gen

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

vision-media★ 9↓ 1.9k✓ v0.12.2 scan passed
Updated 10/16/2026
v0.9.36
@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).

vision-media★ 8↓ 1.6k
Updated 10/16/2026
v0.7.1
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,

vision-media★ 12↓ 883✓ v0.7.1 scan passed
Updated 10/16/2026
v0.1.4
dsh-video-preview

Video Preview

Inline video preview for dsh-better-sidebar: plays .mp4/.webm/.mov/.mkv/.avi etc. in the sidebar editor with HTTP Range (seeking) support via a dedicated /video host route

vision-mediaui-customization★ 5↓ 1.4k
Updated 10/16/2026
v3.16.6
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.

ui-customizationvision-media★ 9↓ 819✓ v3.16.6 scan passed
Updated 10/16/2026
v0.6.1
dsh-film

Film

VibeDev 影视工作台：在 DeepSeek Harness 和 VibeDev 的右侧栏打开画布式影视工作台（剧本、分镜画布、图片/视频/音频生成、剪辑成片），模型与费用统一走 VibeDev 账号 · VibeDev Film: a canvas film workbench in the right sidebar of DeepSeek Harness and VibeDev (script, storyboard canvas, image/video/audio generation, e

vision-media★ 3↓ 2k
Updated 10/16/2026
v0.5.0
dsh-ffmpeg

Ffmpeg

DSH video processing tools plugin: ten tools—ffmpeg_probe/cut/concat/encode/subtitle/extract/gif/frames/adjust/health—for probe summaries, batch frame extraction, GIF creation, speed/volume/mute/rotation adjustments; processes use the official subprocess service, with process-tree termination on tim

vision-media★ 6↓ 1.1k
Updated 10/16/2026
v0.2.5
@mokuyoaxis/dsh-iris

Iris

Multi-provider image, video, music, and speech generation, transcription, visual understanding, and prompt optimization with an integrated Iris workbench for DeepSeek Harness.

vision-media★ 8↓ 834✓ v0.2.5 scan passed
Updated 10/16/2026
v0.2.1
dsh-image-pathify

Image Pathify

DeepSeek Harness plugin: let text-only models receive pasted images, and analyze them with a built-in OpenAI-compatible vision tool

vision-media★ 4↓ 1.5k✓ v0.2.1 scan passed
Updated 10/16/2026
v0.6.1
dsh-live-voice

Live Voice

Local-first hands-free AI voice assistant plugin for DeepSeek Harness (DSH), with speech-to-text, text-to-speech, voice commands, and local speech engines.

vision-media★ 6↓ 961
Updated 10/16/2026
v0.2.6
@try-works/dsh-stt

Stt

Multi-model local speech-to-text for the DSH Web composer: Whistle and Voz, user-selectable, with lazy per-model download. Ships as a DSH bundle.

vision-media★ 2↓ 2.1k
Updated 10/16/2026
v0.10.1
dsh-tool-vision

Tool Vision

DeepSeek Harness external vision model plugin: inspect_image sends local images or http(s) image URLs to any OpenAI-compatible endpoint, bringing the vision model's textual response directly back into the conversation; includes a Web UI settings panel.

vision-media★ 8↓ 665
Updated 10/16/2026
v0.5.2
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.

vision-media★ 8↓ 659✓ v0.5.2 scan passed
Updated 10/16/2026
v1.8.2
dsh-speak

Speak

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

vision-mediaintegrations-communication★ 11↓ 482
Updated 10/16/2026
v1.0.8
dsh-free-vision

Free Vision

Free vision plugin for DeepSeek Harness (dsh): image understanding for text-only models with free-tier providers (Qwen3-VL-Flash / DeepSeek-OCR / Doubao). 免费视觉插件：纯文本模型看图能力，优先免费模型（通义千问 / 硅基流动 / 豆包）。

vision-mediamodels-usage★ 7↓ 721
Updated 10/16/2026
v0.1.0
dsh-vision-web

Vision Web

Eyes for text-only DeepSeek on DeepSeek Harness: image understanding via Doubao Web by default (zero cost, no API key), Antigravity IDE quota (flash/pro), Gemini API, or Cockpit proxy — model-invokable vision tool, wrapper adapters, evidence memory, and a

vision-media★ 8↓ 484✓ v0.1.0 scan passed
Updated 10/16/2026
v1.0.10
dsh-mmx-bridge

Mmx Bridge

MiniMax multimodal bridge for DeepSeek Harness (DSH). One mmx_bridge tool covers describe/image/video/speech/music/cover/search/quota; optional web_search/read_image takeover; built-in client enhancement renders inline players/previews plus a settings-pag

vision-mediaintegrations-communication★ 10↓ 388✓ v1.0.10 scan passed
Updated 10/16/2026
v0.6.4
@wszhoho/dsh-file-attachment

File Attachment

File attachments: drag, paste, or upload files (multiple files supported); images and documents are saved uniformly to .dsh-file-attachment and sent using @absolute-path references (works with text models); inline image thumbnail previews and file entries are shown in the input box, while images in

vision-mediaproductivity-workflow★ 2↓ 1.2k✓ v0.6.4 scan passed
Updated 10/16/2026
v0.3.6
dsh-voice

Voicealt · STARDUSTLC666

DSH voice plugin: edge-tts Microsoft neural speech synthesis (free, no key required) + OpenAI-compatible speech-to-text, with plugin-level proxy support.

vision-media★ 4↓ 705
Updated 10/16/2026
123…21Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in