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.

CATEGORY

Vision & Media DSH plugins

Verified manifests and exact versions in this category.

All categories

All pluginsAgents & Orchestration1.5kMemory & Context2.1kCoding & Developer Tools4kUI & Customization5.6kIntegrations & Communication3kVision & Media917Search & Research1.2kSecurity & Access1.8kModels & Usage2.5kProductivity & Workflow3.6k

All plugins

915 plugins
v0.1.1
dsh-yali-image-generator

Yali Image Generator

DeepSeek-Harness 图像生成插件。申请 Yali AI API Key：https://api.yaliai.com/

↓ 21★ 1
Updated 11/4/2026
v0.7.0
dsh-lanhu

Lanhu

Let AI directly “read Lanhu designs” and parse them into precise, ready-to-copy values (colors / font sizes / corner radii / spacing / text), replacing estimation from screenshots.

↓ 43
Updated 11/4/2026
Cv0.3.2
dsh-computer-use

Computer Use

Computer Use plugin: virtual mouse human-like operation + native vision model integration (deepseek-v4-flash-vision-exp directly reads screenshots), 12 model-friendly tools including screen_observe

↓ 0★ 40
Updated 10/5/2026
v0.2.2
vision-translation-dsh

Vision Translation Dsh

Native dsh (DeepSeek Harness) Cordis plugin adapter for vision-translation: grounds images into <vision-context> via the Python CLI (PROTOCOL v1). Spawns cli.py, never re-implements core logic.

↓ 19★ 1
Updated 11/4/2026
v0.9.1
dsh-display-panel

Display Panel

Display tab for the DeepSeek Harness Web UI: watch and drive the AI's own per-session display, including per-session resolution (presets 480p/720p/1080p/2K/4K, custom sizes, adaptive) changed live without restarting the display.

↓ 38★ 0
Updated 11/4/2026
v0.1.1
dsh-ocr-bridge

Ocr Bridge

Paste images into DeepSeek Harness chat and have them read by a free local backend (macOS Vision / Tesseract) before the text-only DeepSeek model answers

↓ 37★ 0
Updated 11/4/2026
v0.3.0
@maxwell-feng/dsh-windows-ocr

Windows Ocr

dsh plugin: recognize attached images with the built-in Windows OCR engine (Windows.Media.Ocr) and send only the recognized text to the model. Text models never receive image bytes; vision passthrough is opt-in.

↓ 37★ 0
Updated 11/4/2026
v0.1.2
dsh-vision-autoswitch

Vision Autoswitch

DeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.

↓ 35★ 0
Updated 11/4/2026
v0.1.0
@zoytown/dsh-avatar

Avatar

DeepSeek Harness (dsh) plugin for wallpaper theming — upload images from the Settings page, pick one, and the whole dsh web UI renders over it with an adjustable readability mask and blur.

↓ 35★ 0
Updated 11/4/2026
v0.3.3
@opensquad/dsh-voice-input

Voice Input

SenseVoice voice input plugin for DeepSeek Harness: adds a microphone button next to the conversation input box, records audio, and uses the local SenseVoice service to convert it to text and fill the input box. On first use, it automatically downloads the model and displays progress; the backend is

↓ 35★ 0
Updated 11/4/2026
Vv0.5.4
dsh-voice-scribe

Voice Scribe

Voice input plugin for DSH: tap or hold Alt to talk, then release or tap again to convert speech to text. Supports a hotword replacement list (hot.txt), custom polishing prompts, and a recording level indicator. Uses local offline recognition by default (SenseVoice; zero configuration, zero key, and

↓ 0★ 35
Updated 10/24/2026
v0.1.0
@zzdream67/dsh-vision-bridge

Vision Bridge

Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.

↓ 33★ 0
Updated 11/4/2026
v0.1.0
dsh-tool-image-gen

Tool Image Gen

DSH tool plugin: generate images through ToAPIs async GPT-Image-2 API (submit task, poll, download).

↓ 32★ 0
Updated 11/4/2026
v0.3.0
@toddzheng024/vapor-generation-fal

vapor-generation-fal

Vapor generation fal tool operations

↓ 29
Updated 11/4/2026
v0.3.0
@toddzheng024/vapor-vlm-modal

Vapor · Modal Qwen

Batch visual inspection with source versions, explicit coverage and recoverable cloud jobs

↓ 26
Updated 11/4/2026
v0.1.7
dsh-agent-voice

Agent Voice

DeepSeek Harness plugin: gives the agent a voice — it reads completed tasks and attention requests aloud (never reasoning or interim reports) via local Piper / XTTS v2, with a settings panel and a curated set of voices.

↓ 26★ 0
Updated 11/4/2026
v0.2.1
dsh-local-vision

Local Vision

DeepSeek Harness plugin: a model-callable local_vision tool that describes images with a local vision model through Ollama. No cloud, the image never leaves the machine. Two tiers: fast (text/colors/summary) and detailed (full description).

↓ 12★ 1
Updated 11/4/2026
v0.1.0
dsh-bundle-vision

Bundle Vision

Vision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes

↓ 25★ 0
Updated 11/4/2026
v0.6.4
dsh-media-skills

Media Skills

Free image reading and generation for DeepSeek Harness: vision QA, illustration generation, provider fallback, no bundled keys, and a 创作 page in the sidebar (desktop 0.2.1+) with model, ratio and 1K–4K pickers.

↓ 0★ 25
Updated 11/2/2026
Rv0.15.0
dsh-ros2

Ros2

ROS2 debugging tools and diagnostics skills for DeepSeek Harness (DSH): package/workspace/dependency inspection, node/topic/service/action/param/interface enumeration, topic sampling, TF tree, graph topology JSON, approval-gated builds and message scaffolding, GUI screenshot and multimodal vision ob

↓ 0★ 25
Updated 8/24/2026
v0.1.2
@freespace8/dsh-free-vision

Free Vision

Local image understanding for the DeepSeek Harness: OCR, table-layout detection, and semantic description of textless images via macOS Vision, fully on-device (images never leave your Mac). 本地化识图，图片不出本机。

↓ 11★ 1
Updated 11/4/2026
v0.1.1
@aetheri-ai/dsh-show-image

Show Image

DeepSeek Harness plugin: a model-facing show_image tool that presents a local image to the human viewer in the conversation.

↓ 22★ 0
Updated 11/4/2026
v0.1.10
dsh-photo-pet

Photo Pet

Photo pet plugin for the DeepSeek Harness (DSH) Web GUI: turn any uploaded photo into a floating pet that can be dragged, dressed up and chatted with. 照片宠物插件:把上传的照片变成 DSH Web GUI 里的浮动宠物,可拖拽、可换装、会说话

↓ 21★ 0
Updated 11/4/2026
v0.1.1
dsh-qr-toolkit

Qr Toolkit

QR code & barcode toolkit for DeepSeek Harness: decode images (PNG/JPEG, local or URL) and generate QR codes as PNG. 二维码/条码工具箱：解码与生成。

↓ 18★ 0
Updated 11/4/2026
v0.1.4
dsh-seework

Seework

SeeWork — DeepSeek Harness plugin for SeeAI Hub: generate images inside the agent conversation with your own SeeAI Hub API key (OpenAI-compatible /v1/images/generations), browse everything you generated in the sidebar material library, and arrange it on a

↓ 16★ 0
Updated 11/4/2026
v0.4.1
dsh-visual-plugin

Visual Plugin

Local-first visual media plugin for DeepSeek Harness: local video preprocessing, native vision, copyable image history, and video playback.

↓ 0★ 16
Updated 10/7/2026
v0.1.1
@try-works/dsh-vision-worker

Vision Worker

DeepSeek Harness plugin: a vision worker over Cloudflare Workers AI (@cf/moonshotai/kimi-k2.6) that routes image requests from text-only callers, returns a versioned righthand.vision.v1 envelope, and supports follow-up questions.

↓ 15
Updated 11/4/2026
Tv3.0.2
dsh-tavern-image

Tavern Image

DSH Tavern 剧情配图插件，支持 ComfyUI、NovelAI、OpenAI Images、Gemini 等渠道。

↓ 0★ 15
Updated 10/21/2026
v0.1.3
@pzqian123/dsh-tool-vision

Tool Vision

DSH plugin: read images through a user-configured vision-capable model when the main model route cannot accept image input

↓ 14★ 0
Updated 11/4/2026
v1.0.0
texteye

Texteye

DeepSeek Harness plugin: convert images to ASCII art + per-cell color map so text-only models can see them.

↓ 4★ 2
Updated 11/4/2026
← Previous1…56789…31Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in