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 — Page 14

CATEGORY

Vision & Media DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1042Memory & Context1300Coding & Developer Tools2786UI & Customization3656Integrations & Communication1910Vision & Media615Search & Research865Security & Access1268Models & Usage1682Productivity & Workflow2234

All plugins

614 plugins
Iv0.1.0
dsh-image-webp-to-png

Image Webp To Png

Re-encode WebP attachment request-images to PNG for LLM backends (e.g. llama.cpp) that cannot decode WebP. Fixes the '400: Failed to load image or audio file' error for alpha-channel images.

vision-media★ 0↓ 0
Updated 10/6/2026
v0.1.2
sh-volume-shuff

Sh Volume Shuff

Read the newest turn aloud from the DSH composer: a speaker button in the composer tool row, left of the model selector, that reads from the start of your newest question, scrolls the page to that spot and marks it with a blinking caret on one click, stops on the next, press-and-hold the icon to pic

vision-media↓ 0
Updated 10/6/2026
Cv1.1.1
dsh-conversation-screenshot

Conversation Screenshot

Copy a full-length screenshot of the DSH conversation to the clipboard.

vision-media★ 0↓ 0
Updated 10/6/2026
Sv0.1.1
dsh-shot

Shot

Composer screenshot control for DeepSeek Harness: box-select and annotate a screen capture in an in-window overlay, optionally hiding the DSH window while capturing, then send the result as an image attachment.

vision-mediaui-customization★ 0↓ 0
Updated 10/6/2026
Av0.2.0
@dsh-external/dsh-agnes-image

Agnes Image

Agnes Image 2.5 Flash (agnes-image-2.5-flash) generation tool for DeepSeek Harness: text-to-image, image-to-image and multi-image composition, saved straight into the session workspace.

vision-media★ 0↓ 0
Updated 10/6/2026
v0.1.1
dsh-computer-use-mode

Computer Use Mode

Computer-use mode for DeepSeek Harness: native-resolution screen capture plus mouse, keyboard and window control, for operating software that has no agent-facing integration.

vision-media★ 0↓ 0
Updated 10/6/2026
Sv0.1.1
shengcheng

Shengcheng

DSH plugin: generate images with logged-in Grok/GPT accounts, and videos with Grok.

vision-media★ 0↓ 0
Updated 10/6/2026
Dv0.1.0
dsh-dynamic-bg

Dynamic Bg

Add full-screen dynamic backgrounds to DSH: supports static images, GIFs, and videos, with adjustable overlays, blur, opacity, and translucent panels. Only modifies CSS variables; does not touch hashed class names.

ui-customizationvision-media★ 0↓ 0
Updated 10/5/2026
Fv0.2.0
dsh-free-media

Free Media

DSH 免费多模态三件套:文生图(智谱 CogView-3-Flash 2.1MP / Pollinations 零 Key 兜底)、零 Key 视频理解(ffmpeg 抽帧)、免费文生视频/图生视频(智谱 CogVideoX-Flash / Agnes)。注册 free_image_generate / video_extract_frames / free_video_generate 三个工具,并附带 free-media skill。

vision-media★ 0↓ 0
Updated 10/5/2026
Mv0.1.0
dsh-media-viewer

Media Viewer

右侧栏媒体预览:直接预览视频、音频和 HTML(大文件可拖进度条,HTML 默认允许脚本),并提供文件夹媒体画廊,需配合 dsh-better-sidebar · Inline video, audio and HTML preview plus a folder media gallery in the dsh-better-sidebar right column — range-streamed large files, sandboxed HTML with working relative assets

vision-mediaui-customization↓ 0
Updated 10/5/2026
Iv0.1.0
dsh-image-edge-cap

Image Edge Cap

Caps the longest side of images sent to chosen providers or models in DeepSeek Harness, with its own Settings tab

vision-media★ 0↓ 0
Updated 10/5/2026
v0.1.1
@xp1024/dsh-voice-gateway

Voice Gateway

Voice Gateway client surface for DeepSeek Harness: mic status, voiceprint filtering, and auto-speak

vision-media★ 0↓ 0
Updated 10/4/2026
Mv0.1.1
dsh-minimax-multimodal

Minimax Multimodal

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

vision-media★ 0↓ 0
Updated 10/4/2026
Vv0.1.0
dsh-video-see

Video See

Look at video with your own eyes: a DeepSeek Harness plugin that samples frames with ffmpeg and returns them to the agent as real images, each labelled with its timestamp — no vision API, no API key, nothing leaves the machine.

vision-media★ 0↓ 0
Updated 10/4/2026
Ov0.1.0
dsh-opencode-eyes

Opencode Eyes

DeepSeek Harness plugin: gives a text-only model eyes. It mounts the bundled opencode-eyes MCP server, which sends an image file to StepFun's step-3.7-flash vision model and returns a detailed description, as the tool mcp__opencode_eyes__describe_image.

vision-mediaintegrations-communication★ 0↓ 0
Updated 10/4/2026
Ov0.1.0
dsh-opencode-eyes-nvidia

Opencode Eyes Nvidia

DeepSeek Harness plugin: eyes for text-only models through NVIDIA NIM. It mounts the bundled opencode-eyes-nvidia MCP server, which sends an image to a hosted vision model (MiniMax-M3 by default) and returns a description, exposing mcp__opencode_eyes_nvidia__describe_image and mcp__opencode_eyes_nvi

vision-mediaintegrations-communication★ 0↓ 0
Updated 10/4/2026
Pv0.1.0
dsh-ppocr

Ppocr

DeepSeek Harness plugin: local OCR. It mounts the bundled PP-OCRv6 Medium stdio MCP server (PaddleOCR/PaddleX on ONNX Runtime, CPU only) and exposes mcp__ppocr__ocr_image and mcp__ppocr__ocr_pdf, so images and PDFs can be read without sending them anywhere.

vision-mediaintegrations-communication★ 0↓ 0
Updated 10/4/2026
Tv0.1.0
dsh-tokenrhythm-image

Tokenrhythm Image

DeepSeek Harness plugin: image generation through TokenRhythm. It mounts the bundled zero-dependency stdio MCP server, which generates images with qwen-image-2.0 or wan2.7-image and saves them to disk, exposing mcp__tokenrhythm_image__generate_image and mcp__tokenrhythm_image__list_image_models.

vision-mediaintegrations-communication★ 0↓ 0
Updated 10/4/2026
Sv0.1.0
dsh-simple-image

Simple Image

DeepSeek Harness plugin: text-to-image through a StepFun-compatible /images/generations endpoint. It mounts the bundled zero-dependency stdio MCP server behind a small NDJSON bridge and exposes mcp__simple_image__simple_image.

vision-mediaintegrations-communication★ 0↓ 0
Updated 10/4/2026
Iv0.1.0
dsh-image-gen-mcp

Image Gen Mcp

DeepSeek Harness plugin: image generation through a configurable, provider-agnostic backend. It mounts the bundled stdio MCP server behind an NDJSON bridge, exposing mcp__image_generation__image_generate and mcp__image_generation__image_config_status, and registers the bundled image-generation skill

vision-mediaintegrations-communication★ 0↓ 0
Updated 10/4/2026
Vv0.1.0
dsh-voice-f9

Voice F9

全局「按住说话」语音输入:按住 F9 说话、松手出字,任意 Windows 程序可用;本地 SenseVoice 识别,不联网、不占显卡。Hold-to-talk voice input for any Windows app, local SenseVoice via sherpa-onnx.

vision-media★ 0↓ 0
Updated 10/3/2026
Vv0.3.0
dsh-voice-mimo

Voice Mimo

Voice for DeepSeek Harness backed by Xiaomi MiMo: browser-native 🎤/🔊 UI (MiMo TTS read-aloud) + voice_transcribe/voice_speak calling MiMo ASR/TTS directly, with a configurable voice map and in-conversation speech strips. Fork of zhuiyueya/dsh-voice (MIT).

vision-media★ 0↓ 0
Updated 10/3/2026
Mv0.2.1-alpha.1-r1
dsh-mimo-agent-tools

Mimo Agent Tools

Xiaomi MiMo search + multimodal tools for DSH agents: mimo_search/vision/audio/video/asr/tts.

vision-media★ 0↓ 0
Updated 10/3/2026
Pv0.1.0-alpha.1
dsh-page-evidence

Page Evidence

Page-aware PDF evidence for DeepSeek Harness: expose unread pages, run optional local OCR, and preserve exact quote locations.

vision-media★ 0↓ 0
Updated 10/3/2026
Ov2.0.0
dsh-openrouter-imagen-v2

Openrouter Imagen V2

DSH plugin v2: a standalone image-generation workspace (sidebar entry + its own main view) for the OpenRouter Image API — chat-style prompt column, picture area with history, draggable parameters.

vision-mediaui-customization★ 0↓ 0
Updated 10/2/2026
Jv0.3.0
dsh-jimeng

Jimeng

即梦(火山方舟 Seedream) text-to-image/image-to-image plugin: model tools generate_image / image_to_image (image-to-image supports 1–10 reference images, view images directly in the tool card) + settings panel for editing API configuration + manual image generation panel (multi-image selection)

vision-media★ 0↓ 0
Updated 10/2/2026
Cv0.6.1
dsh-character-emote-plugin

Character Emote Plugin

Character expression portrait plugin: multiple characters + automatic streaming emotion detection (llm/stream keyword rules; automatically switches images if the model forgets to call the tool) + compound emotions + mood baseline + draggable/scroll-wheel zoomable portraits + portrait switching anima

ui-customizationvision-media★ 0↓ 0
Updated 10/2/2026
Vv1.0.0
dsh-voice-context

Voice Context

Voice-to-text for DeepSeek Harness: a composer mic button backed by a cloud STT provider (SiliconFlow) or a bundled offline backend (FunASR / faster-whisper).

vision-media★ 0↓ 0
Updated 10/2/2026
Sv0.4.2
dsh-splash-animation

Splash Animation

DSH splash animation: includes a default video and works immediately after installation; you can also replace it with your own video in the settings. After playback, the interface is revealed with a 0.3-second fade-out, replacing the shell’s own loading screen. Clear the path to disable it completel

ui-customizationvision-media★ 0↓ 0
Updated 10/2/2026
Tv1.0.0
dsh-tool-ocr

Tool Ocr

Extract text from images and PDFs in DeepSeek Harness: read a born-digital text layer, or OCR a scan with any engine you configure.

vision-media★ 0↓ 0
Updated 10/2/2026
← Previous1…1213141516…21Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in