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 9

CATEGORY

Vision & Media DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1030Memory & Context1293Coding & Developer Tools2799UI & Customization3662Integrations & Communication1903Vision & Media615Search & Research864Security & Access1275Models & Usage1677Productivity & Workflow2232

All plugins

607 plugins
Rv0.4.0
@chenjie1129/dsh-remotion-video-plugin

Remotion Video Plugin

Remotion video creation and verified rendering plugin for DeepSeek Harness

vision-media★ 2↓ 0
Updated 8/22/2026
Tv0.1.0-rc.6
@deepseek-ai/dsh-tool-vision-read

Tool Vision Read

DSH plugin: vision_read — route image reading to a dedicated vision model (e.g. Kimi K3) so text-only agents can see images

vision-media★ 2↓ 0
Updated 8/21/2026
Av0.1.1
dsh-antv-infographic

Antv Infographic

AntV Infographic renderer for DeepSeek Harness: render AI-generated infographic fences inline with streaming, editing, and SVG/PNG export.

vision-mediaui-customization★ 2↓ 0
Updated 8/21/2026
Vv0.4.4
dsh-vision-skill

Vision Skill

DSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR, paste-to-path (no framework patch). 8 tools + runtime skill.

vision-media★ 2↓ 0
Updated 8/21/2026
Ov0.1.0
@dsh-external/dsh-ocr1-memory

Ocr1 Memory

Based on the DeepSeek-OCR1 optical compressed memory system: renders memories as images for storage, with support for SoM segmentation, age-based decay/blur, activation-based recall, and DSH Agent retrieval

memory-contextvision-media★ 2↓ 0
Updated 8/21/2026
Av1.0.2
aura-vision

Aura Vision

Aura Vision — free vision OCR plugin for DeepSeek Harness web profile: Zhipu GLM-4V-Flash (free tier), adaptive tile recognition for long documents, history with favorites and Markdown/Excel/Word/PNG export.

vision-media★ 2↓ 0
Updated 8/20/2026
Tv0.3.1
taxue-dsh-artisan

Taxue Dsh Artisan

taxue artist: reverse-engineers image/video prompts, extracts deterministic color palettes, audits and optimizes prompts, and generates images through multiple providers (with optional image control), while bridging taxue-imagegen’s template slot filling and output acceptance.

vision-media★ 1↓ 0
Updated 10/16/2026
Lv1.6.2
dsh-live2d-voice

Live2d Voice

Live2D session view with realtime voice: continuous voice input, streaming TTS, subtitle translation, multi-model catalog, standalone entry / Live2D 实时语音会话视图：连续语音输入、流式 TTS、字幕翻译、多模型目录、独立入口

vision-media★ 1↓ 0
Updated 10/15/2026
Av0.2.0
dsh-auto-image

Auto Image

Bridges images into text for DeepSeek Harness: when the session's selected model cannot see images, a configured vision model describes them and the descriptions enter the durable session history as folded context rows — your message stays untouched.

vision-mediamemory-context★ 1↓ 0
Updated 10/15/2026
Iv0.2.0
dsh-image-tool

Image Tool

DeepSeek Harness image generation and editing tool plugin: connects any OpenAI-compatible image generation/editing service as a platform tool, allowing models to generate or modify images directly in conversations. Images are output as native platform image blocks and displayed in the tool card (thu

vision-mediaintegrations-communication★ 1↓ 0
Updated 10/14/2026
Vv0.3.13
dsh-voice-mini

Voice Mini

Voice-feedback plugin for DeepSeek Harness: a speak tool, readReplies narration, an LLM verbalizer pass, per-session voices, chimes, a monitoring panel, and a native macOS floating pet. zh/en i18n.

vision-mediaui-customization★ 1↓ 0
Updated 10/13/2026
Pv1.4.1
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.

vision-mediaui-customizationmodels-usage★ 1↓ 0
Updated 10/13/2026
v0.4.0
@little-traincar/dsh-imagegen

Imagegen

Image generation tool for DeepSeek Harness 0.2.x — provider-table driven (Doubao Seedream / Aliyun qwen / any OpenAI-compatible gateway / local deployments), user-configurable model per channel, watermark-free, inline in-chat display.

vision-mediamodels-usage★ 1↓ 0
Updated 10/13/2026
Nv0.2.0
dsh-neon-splash-v3

Neon Splash V3

DSH desktop opening animation: pure black opening, progressive deblurring and brightening, automated terminal startup and workspace model connection, plugin preloading, login interface, AI voice greeting, AR HUD compilation sequence, and code-filled transition into the main interface.

ui-customizationvision-media★ 1↓ 0
Updated 10/12/2026
Sv1.1.1
dsh-screenshot-xn

Screenshot Xn

DSH Screenshot (xn): Full-screen WeChat-style region selection and annotation (rectangle/ellipse/arrow/brush/mosaic/text, with undo/redo), with one-click insertion into chat, copying, or saving as; selected regions can be OCR-recognized and translated (offline recognition + reuse of models already c

vision-media★ 1↓ 0
Updated 10/11/2026
Vv0.3.0-rc.7
@local/dsh-video-wallpaper

Video Wallpaper

Local image and looping-video wallpapers for the DeepSeek Harness Desktop and Web UI

ui-customizationvision-media★ 1↓ 0
Updated 10/11/2026
Kv0.4.3
kkj-luna-dsh-image-bridge

Kkj Luna Dsh Image Bridge

生图桥: Connect models without image generation/editing capabilities to external image generation models. Configure the API and key in the Web interface, and the model can directly call image generation and editing capabilities.

vision-mediaintegrations-communication★ 1↓ 0
Updated 10/11/2026
Lv1.1.0
dsh-local-ocr

Local Ocr

Offline OCR tool for DeepSeek Harness: registers an ocr tool that runs the bundled ocr_tool.py (Windows native OCR, then RapidOCR, then Tesseract) over images and PDFs.

vision-media★ 1↓ 0
Updated 10/11/2026
Mv0.1.5
dsh-multi-tts

Multi Tts

Text-to-speech (MiniMax / OpenAI-compatible TTS, selectable provider and voice)—a read-aloud button beside each reply, an auto-read toggle for the input box, and provider and voice selection in the settings page. Zero build, pure JS.

vision-media★ 1↓ 0
Updated 10/11/2026
Iv0.1.1
@dsh-plugin/dsh-image-annotate

Image Annotate

An annotation pen for the DeepSeek Harness image lightbox: draw, label, then move / resize / re-edit any mark, and send the annotated PNG straight into the composer. 给 DSH 图片预览加一支画笔。

vision-mediaui-customization★ 1↓ 0
Updated 10/10/2026
Pv0.3.1
dsh-picflow

Picflow

DeepSeek Harness plugin: pasted screenshots become numbered image references. Every Ctrl+V image is admitted to the official attachment library with a stable 图片N number, listed in a composer-dock thumbnail panel with an @图片 source and a zoom overlay, can be inserted as a native reference chip at the

vision-mediaproductivity-workflow★ 1↓ 0
Updated 10/9/2026
Vv0.3.0
dsh-v4flash-tiler

V4flash Tiler

DSH plugin: auto-tiles oversized chat images into labelled grid pieces (row/col metadata, overlap-aware, multi-image group isolation) so the DeepSeek vision model keeps fine detail instead of the ~800px downsample.

vision-media★ 1↓ 0
Updated 10/8/2026
Vv0.1.0
dsh-voice-ptt

Voice Ptt

Push-to-talk dictation for DeepSeek Harness: hold a single key in the composer, release, and the transcript is inserted into your draft.

vision-media★ 1↓ 0
Updated 10/7/2026
Bv1.1.1
dsh-boot-animation-sound

Boot Animation Sound

DSH startup animation: play a video across the entire window; sound does not require full screen. You can choose when it is triggered (app launch/page refresh/new conversation/any session) and how often it plays (every time/once a day/once only/limited to N plays).

ui-customizationvision-media★ 1↓ 0
Updated 10/6/2026
Cv1.0.0
dsh-composer-glass

Composer Glass

DSH plugin: one uniform frosted-glass material for the UI surfaces, plus an optional image/video dynamic wallpaper behind them.

ui-customizationvision-media★ 1↓ 0
Updated 10/6/2026
Pv0.1.0
dsh-plugin-aivideo-shotkit

Plugin Aivideo Shotkit

AI video storyboard cutting and character replacement workflow plugin: automatically detects player UI overlays and black bars, splits footage into shots by scene, evaluates replaceability shot by shot, and exports clips and workflow packages that can be directly fed into face-swapping/action-transf

vision-mediaproductivity-workflow★ 1↓ 0
Updated 10/5/2026
v0.1.1
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.

ui-customizationvision-media★ 1↓ 0
Updated 10/2/2026
Sv0.1.0-alpha.1
dsh-sensenova-vision-aid

Sensenova Vision Aid

Unofficial DeepSeek Harness vision plugin: when the main model receives an image-recognition request, it spawns a child agent switched to the SenseNova vision model (reusing the dsh-sensenova-freeapi credential), with a dedicated settings panel and a direct fallback path.

vision-media★ 1↓ 0
Updated 10/2/2026
Iv0.2.0
dsh-imgdraw

Imgdraw

Text-to-image for DeepSeek Harness: a `draw_image` model tool, an input-bar 生图 button with a prompt popup (async generation, 4-grid results, download / keep / delete), an /imgdraw image route, and persisted history. Backends: DashScope wan2.7-image (free default) and SiliconFlow Qwen-Image.

vision-media★ 1↓ 0
Updated 10/2/2026
Mv3.16.6
dsh-modlens

Modlens

Plug-in vision for text-only LLMs — a DeepSeek Harness (dsh) fork of ModLens adding multi-engine support (Gemini, Volcengine Ark/Doubao, Claude) and per-call engine selection

vision-mediamodels-usage★ 1↓ 0
Updated 10/2/2026
← Previous1…7891011…21Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in