DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

Plugins Presets Docs News

Community

Publish a plugin Contact Report an issue

Resources

Plugin Hub on GitHub DeepSeek Harness System status Privacy 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 plugins Agents & Orchestration1.5k Memory & Context2.1k Coding & Developer Tools3.9k UI & Customization5.6k Integrations & Communication3k Vision & Media913 Search & Research1.2k Security & Access1.8k Models & Usage2.4k Productivity & Workflow3.6k

All plugins

912 plugins

dsh-image-forge

Image Forge

DeepSeek Harness plugin: Qwen-Image text-to-image generation / reference image editing, with wh_ratio from the official prompt contract as a first-class parameter; backends api (cloud key) / comfyui (local ComfyUI), default auto; results archived by canvas.

Updated 11/4/2026✓ Scan passed

dsh-ears-prosody

Ears Prosody

Give DeepSeek Harness a pair of ears: turn audio into “how it was said,” not “what was said.” A zero-dependency local acoustic layer, with a WeChat-style chat skin, a “press and hold to talk” recording button, and clickable playback voice bars (merged from dsh-wechat-bubbles starting in 0.3.0). Auto

↓ 283

Updated 11/4/2026✓ Scan passed

@nextnowlabs/dsh-ark-toolkit

Ark Toolkit

DSH Ark Toolkit: Integrates ByteDance Volcano Ark’s text-to-image and speech synthesis capabilities into DeepSeek Harness. Includes Doubao Seedream text-to-image (ark_generate_image) and Doubao Speech Synthesis Model 2.0 (ark_speak).

Updated 11/4/2026✓ Scan passed

dsh-genbox-plugin

Genbox Plugin

DeepSeek Harness tools for GenBox: image generation/editing (including inpaint, upscale, cutout) and video generation through a local GenBox server.

Updated 11/4/2026

dsh-image-studio

Image Studio

DeepSeek Harness plugin: local text-to-image with a canvas-style GUI, inpainting, DeepSeek vision review, OpenAI-compatible API option, and a Python Stable Diffusion worker (diffusers/MPS).

Updated 11/4/2026✓ Scan passed

@maxwell-feng/dsh-tesseract-ocr

Tesseract Ocr

dsh plugin: recognize attached images locally with Tesseract OCR and send only the recognized text to the model. Text models never receive image bytes; vision passthrough is opt-in.

Updated 11/4/2026

dsh-vision-guard

Vision Guard

Transparent image guard + vision analysis for DeepSeek Harness: text-only models read pasted images without the 400 session deadlock.

Updated 11/4/2026✓ Scan passed

computer-user-vision

Computer User Vision

Unofficial fork of computer-user by jing-hy: Codex-style Windows computer use for DeepSeek Harness. Clicks target live UI Automation element refs (ref/name) rather than pixels estimated off a downscaled screenshot, so they land exactly; screenshots ride the tool result as real images and carry an ex

Updated 11/4/2026

dsh-plugin-image-tools

Plugin Image Tools

DSH image plugin with three tools for three scenarios: ask_user_choice for image/image-text mixed selection cards (rendered in the Web GUI, with zoom support), show_images for embedding images in replies (mixed text and images), and save_received_images for receiving images with vision-blind models

Updated 11/4/2026✓ Scan passed

Dictate

Context-aware voice input for DeepSeek Harness with Web Speech, local SenseVoice transcription, model polish, editable Composer drafts, and user-controlled sending

Updated 11/4/2026

@a9i5k4/dsh-ark9canvas

Ark9canvas

DSH image generation plugin Ark9canvas: Agent image generation (user approval required by default) + floating image generation workbench (aspect ratio/transparent background/batch/prompt library/multiple channels/generation history), supporting text-to-image/image-to-image via OpenAI-compatible imag

Updated 11/4/2026✓ Scan passed

@motong/dsh-voice

Voice

A community plugin that adds voice capabilities to DeepSeek Harness (DSH / DeepSeek Hermes): voice input in the input field (with configurable shortcut) and spoken responses (Microsoft Edge neural voices, with voice switching and preview), with no API key required.

Updated 11/4/2026✓ Scan passed

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.

Updated 9/28/2026✓ Scan passed

Ui Spec

DeepSeek Harness plugin that turns UI screenshots into implementation-grade web specs using OCR, deterministic geometry, scene graphs, assets, and render comparison.

Updated 11/4/2026

@chang416/deepsee

Deepsee

DeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery

Updated 11/4/2026

dsh-plugin-qwen-image

Plugin Qwen Image

DeepSeek Harness out-of-tree plugin: give a text-only coding model eyes by routing images to a Qwen-VL (DashScope) route through ctx.llm and returning text.

Updated 11/4/2026

@muxiva/dsh-voice

Voicealt · @muxiva

Local-first, full-duplex voice for DeepSeek Harness, orchestrated by Muxiva

Updated 11/4/2026

@alain-prot0s5/dsh-screenshot

Screenshot

Screenshot-to-input for DeepSeek Harness: composer camera button + global hotkey (Alt+A) + listener bound to the app lifecycle, configurable in settings. 截图自动粘贴到 DSH 输入框：相机按钮 + 全局快捷键 + 生命周期绑定 + 设置页配置。

Updated 11/4/2026

dsh-voice-studio

Voice Studio

DeepSeek Harness plugin: local TTS, voice cloning and best-effort dubbing with a settings GUI and a dsh_voice tool (XTTS v2 + Piper, faster-whisper, ElevenLabs API option).

Updated 11/4/2026✓ Scan passed

scientific-figure-library

Scientific Figure Library

Local image-code knowledge library with native macOS and local Web clients, plus MCP and Skill for Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.

Updated 10/26/2026

@showin2333/dsh-plugin-share-image

Plugin Share Image

DeepSeek Harness plugin that shares selected conversation messages as a PNG card.

Updated 11/4/2026

@omdp/dsh-vision-bridge

Vision Bridge

DSH Vision Bridge plugin: Automatically distinguishes multimodal and text models. Multimodal models view images directly; text models use a configurable multimodal endpoint (baseUrl + apiKey + model) to view them on their behalf. Supports pasted images, the read_image tool, and converting images int

Updated 11/4/2026

Auto Vision

DSH (DeepSeek Harness) image integration plugin: pasted images are added only to the conversation, not the model request (llm/stream cleanup), and the see_image tool is registered so text models can view images on demand through any OpenAI-compatible vision API

Updated 11/4/2026

dsh-mac-vision

Mac Vision

Native macOS OCR and Vision tools for DeepSeek Harness

Updated 11/4/2026

Mingmu

明眸 VisionBridge - In-house visual bridge: when a visionless model receives an image, it automatically calls a vision model for recognition and feeds the recognized text back to the main model—seamless, configurable, and upgrade-safe

Updated 11/4/2026

@woyeshishen/dsh-vision-plugin

Vision Plugin

Provides external vision model capabilities for DeepSeek Harness: the text-only primary model uses the describe_image tool to call an external vision model to analyze images and receive a text-only description (multimodal completion). A static Cordis plugin that loads automatically when DSH starts.

Updated 11/4/2026

local-ocr-cli

Local Ocr Cli

Fully-local OCR CLI for text-only LLMs: PaddleOCR-VL first-tier engine with tesseract fallback, dsh plugin included

Updated 11/4/2026

dsh-open-eyes

Open Eyes

Open Eyes for DeepSeek Harness: delegate images to a configurable multimodal model through OpenAI Responses, Chat Completions, or Anthropic Messages.

Updated 11/4/2026✓ Scan passed

@jaxzhou/dsh-mathmatic-symbol

Mathmatic Symbol

DeepSeek Harness plugin: typeset LaTeX as font-free SVG/PNG images, draw geometry and function figures from a declarative spec, convert formulas or SVG into embeddable images, and assemble documents with those images inserted

Updated 11/4/2026

dsh-villager-hmm

Villager Hmm

Plays a vanilla Minecraft villager "hmm" whenever the model hums inside its reasoning chain.

Updated 11/4/2026

← Previous 1…3 4 5 6 7…31 Next →

DeepSeek Harness Plugin Hub

Profiles Plugins Categories News Docs Sign in Manage Profiles

Profiles Plugins Categories News Docs Sign in