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 18

CATEGORY

Vision & Media DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1024Memory & Context1290Coding & Developer Tools2776UI & Customization3637Integrations & Communication1900Vision & Media612Search & Research860Security & Access1256Models & Usage1670Productivity & Workflow2217

All plugins

613 plugins
Lv0.1.0
dsh-llm-multimodal

Llm Multimodal

DSH plugin: Provides image/video generation tools in DSH, based on OpenAI-compatible APIs. Models are automatically discovered from existing llm-pi-ai settings.

vision-media★ 0↓ 0
Updated 8/31/2026
Mv0.1.1
@xiaokaizhou/dsh-media-preview

Media Preview

DSH 插件：在聊天记录中自动将本地音视频/图片路径渲染为可播放的预览组件。When an assistant message or tool result contains a local media path, the path is replaced inline with a playable <audio>/<video>/<img> element backed by same-origin /api/media-preview/* route.

vision-mediaui-customization★ 0↓ 0
Updated 8/31/2026
Iv1.0.3
dsh-image-amnesia

Image Amnesia

Keep native vision, drop historical images before they hit relay providers. Global DeepSeek Harness bundle for every agent.

memory-contextvision-media★ 0↓ 0
Updated 8/31/2026
Vv1.0.0
dsh-voice-control

Voice Control

Voice control for DSH web: speech-to-text into the composer (with auto-send) and spoken playback of assistant replies via the Web Speech API

vision-media★ 0↓ 0
Updated 8/31/2026
Pv0.2.0
dsh-photos

Photos

Photo upload for the DeepSeek Harness composer — native picker feeding the stock paste pipeline

vision-media★ 0↓ 0
Updated 8/31/2026
Mv0.1.0
dsh-multimodal-runtime

Multimodal Runtime

Mogu Multimodal Runtime - DeepSeek Harness 统一多模态能力运行时 (Comfy Local Provider V1)

vision-media★ 0↓ 0
Updated 8/29/2026
Sv0.2.3
dsh-speech-input

Speech Input

A microphone button for DeepSeek Harness that writes browser speech recognition into the composer draft.

vision-media★ 0↓ 0
Updated 8/29/2026
Mv0.1.2
dsh-maclens

Maclens

Bridge Apple's on-device Vision framework (macOS) into DeepSeek Harness: OCR, image classification, face detection, and document layout as local dsh tools. No network, no API key, no daemon.

vision-media★ 0↓ 0
Updated 8/29/2026
Tv1.1.0
dsh-tu4-inline-images

Tu4 Inline Images

Inline images in conversations DSH plugin — renders local image paths in the input box, user messages, and LLM replies directly as images (loopback routing + strong token + multiple-root allowlist + three size presets). Inline local images in DSH web conversations.

vision-mediaui-customization★ 0↓ 0
Updated 8/28/2026
Mv0.1.0
dsh-model-auto-hot-switch

Model Auto Hot Switch

Automatic per-task model hot-switching for DeepSeek Harness (dsh): image-aware tasks route to the vision model automatically, every other task keeps your default model. Zero extra tokens, no context disturbance.

models-usagevision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-obb

Xby Obb

检测图像中的旋转目标，输出旋转边界框、角度、置信度和类别标签。支持15个目标类别：plane， ship，storage tank，baseball diamond，tennis court，basketball court，ground track field， harbor， bridge，large vehicle，small vehicle， helicopter， roundabout，soccer ball field，swimming pool。

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-ocr-bank-card

Xby Ocr Bank Card

Identify bank card numbers, issuing banks, and card types; validate card number validity using the Luhn algorithm.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-ocr-captcha

Xby Ocr Captcha

Submit a common CAPTCHA image and return its text.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-ocr-driver-license

Xby Ocr Driver License

Recognizes the main page of a driver's license (license number, name, gender, nationality, address, date of birth, permitted vehicle classes, date of first issuance, validity period) and the secondary page (file number).

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-ocr-handwriting

Xby Ocr Handwriting

Input an image containing handwritten text to automatically detect text lines and recognize their content. Suitable for handwritten notes, signatures, handwritten forms, and more.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-ocr-id-card

Xby Ocr Id Card

Recognizes the front of an ID card (name, gender, ethnicity, date of birth, address, and ID number) and the back (issuing authority and validity period), automatically determines the front or back, and validates the ID number.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-ocr-pass

Xby Ocr Pass

Recognizes the permit number, name, gender, date of birth, validity period, place of issue, and other information on Exit-Entry Permits for Travelling to and from Hong Kong and Macao and Taiwan Travel Permits, with support for MRZ parsing.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-ocr-passport

Xby Ocr Passport

Recognizes passport number, Chinese name, English name, gender, nationality, date of birth, date of issue, expiry date, place of issue, and other information; supports MRZ parsing.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-ocr-pro

Xby Ocr Pro

High-precision text recognition. Input an image containing text to automatically detect and recognize its content. Suitable for various scenarios, including documents, billboards, and screenshots.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-ocr-vehicle-license

Xby Ocr Vehicle License

Recognizes the license plate number, vehicle type, owner, address, make and model, engine number, vehicle identification number, and other information on motor vehicle registration certificates. Supports automatic orientation detection and filtering of primary and secondary pages.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-ocr

Xby Ocr

Text recognition balancing speed and accuracy. Automatically detects and recognizes content in images containing text. Suitable for various documents, billboards, screenshots, and other scenarios.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-pedestrian

Xby Pedestrian

Input an image, detect pedestrians in the image, and output the bounding boxes, confidence scores, and labels for all detected objects.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-pet-detect

Xby Pet Detect

Recognize pet facial expressions and output 4 emotion categories: Angry / Happy / Relaxed / Sad.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-pic

Xby Pic

Includes general text recognition, handwriting recognition, license plate recognition, ID card recognition, everyday object detection, insect recognition, plant recognition, passport recognition, Hong Kong, Macao, and Taiwan travel permit recognition, bank card recognition, business license recognit

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-plant-recognition

Xby Plant Recognition

Identify the plant name (or its family, genus, species, or subspecies).

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-plate-recognition

Xby Plate Recognition

Recognize license plate numbers, license plate colors, single- and double-layer license plates, and bounding boxes.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-pose

Xby Pose

Detect people in images and output bounding boxes and keypoint coordinates. Each person has 17 keypoints, with each point representing a different body part, in order: nose, left eye, right eye, left ear, right ear, left shoulder, right shoulder, left elbow, right elbow, left wrist, right wrist, lef

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-read-pdf

Xby Read Pdf

An MCP server that enables AI assistants to read and analyze PDF files, providing PDF metadata extraction, page-range reading, and keyword search.

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-recog

Xby Recog

Includes general text recognition, handwriting recognition, license plate recognition, ID card recognition, passport recognition, Mainland Travel Permits for Hong Kong, Macao, and Taiwan, bank card recognition, business license recognition, driver's license recognition, and vehicle registration cert

vision-media★ 0↓ 0
Updated 8/28/2026
Xv1.0.0
xby-reflective-vest

Xby Reflective Vest

Input an image, detect whether personnel are wearing reflective clothing, and output bounding boxes, confidence scores, and labels (safe/unsafe) for all targets in the image.

vision-media★ 0↓ 0
Updated 8/28/2026
← Previous1…161718192021Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in