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.

Vision & Media DSH plugins — Page 3

CATEGORY

Vision & Media DSH plugins

Verified manifests and exact versions in this category.

All categories

All plugins Agents & Orchestration716 Memory & Context854 Coding & Developer Tools1.9k UI & Customization2.5k Integrations & Communication1.3k Vision & Media467 Search & Research614 Security & Access861 Models & Usage1.1k Productivity & Workflow1.5k

All plugins

466 plugins

Dictate

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

Updated 9/20/2026

dsh-sound-lab

Sound Lab

DSH 声音工坊（Sound Lab）：Dialogue event sound effects, AI character voice generation, and sound library upload management, all through visual point-and-click controls; includes the 明日方舟安洁莉娜 desktop pet（60fps sprite animation, edge docking, and floating window configuration）. Hot-pluggable dsh plugin.

↓ 91★ 2

Updated 9/20/2026

Sight

Plug-in vision for text-only DeepSeek Harness (dsh) models: a `vision` tool with built-in cheap/free VLM presets, multi-image batch analysis, paste-to-hint image admission, and a web settings page with hot-reload.

Updated 9/20/2026

dsh-screenshot-feedback-hook-mcp

Screenshot Feedback Hook Mcp

Screenshot feedback for DeepSeek Harness — let your coding agent SEE what it builds

Updated 9/20/2026

dsh-auto-vision

Auto Vision

DeepSeek Harness Vision Bridge: automatically discovers your configured multimodal models, equips text-only primary models with a vision tool, and returns recognition results as plain text. Zero configuration, one-command installation.

Updated 9/20/2026

dsh-multimodal-bridge

Multimodal Bridge

DeepSeek Harness plugin bundle: qwen_vision (Qwen-VL image understanding) and qwen_generate (Qwen-Image text-to-image and image editing) tools for text-only models

Updated 9/20/2026

dsh-tool-vision

Tool Vision

DeepSeek Harness external vision model plugin: inspect_image sends local images or http(s) image URLs to any OpenAI-compatible endpoint, bringing the vision model's textual response directly back into the conversation; includes a Web UI settings panel.

Updated 9/20/2026

dsh-vision-recognizer

Vision Recognizer

Adaptive image routing for DeepSeek Harness: pass images directly to native multimodal models and transcribe them only for text-only models.

Updated 9/20/2026✓ Scan passed

dsh-tool-generate-image

Tool Generate Image

Model-facing generate_image tool for DeepSeek Harness (dsh): generates brand-new images with the Google Gemini image-generation service via the Antigravity CLI, saves them, and returns the paths. Hot-pluggable — install with `dsh plugin --profile web add

Updated 9/20/2026

dsh-mac-vision

Mac Vision

Native macOS OCR and Vision tools for DeepSeek Harness

Updated 9/20/2026

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 9/20/2026✓ Scan passed

@eric.wen/dsh-sight

Sightalt · @eric.wen

DeepSeek Harness plugin: direct multimodal image transfer declarations + per-session image clearing, reasoning-effort auto-fill, and progressive Figma MCP bridging (design-to-code + AI-driven design).

Updated 9/20/2026

@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 9/20/2026

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 9/20/2026

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 9/20/2026

@chang416/deepsee

Deepsee

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

Updated 9/20/2026

dsh-seedance2

Seedance2

Generate images and Seedance videos in DeepSeek Harness through the Seedance 2 AI API

Updated 9/20/2026

dsh-vision-plugin

Vision Plugin

dsh-vision-plugin: give DeepSeek Harness text-only models a pair of eyes — pasted images are transcribed by a vision model before they reach a text-only main model, plus the vision_analyze tool and a bilingual settings page.

Updated 9/20/2026

dsh-vision-subagent

Vision Subagent

Capability-aware vision for DeepSeek Harness: native image input for multimodal models, with an isolated one-shot vision-route fallback for text-only models.

Updated 9/20/2026

@woyeshishen/dsh-vision-plugin

Vision Pluginalt · @woyeshishen

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 9/20/2026

dsh-quicksight

Quicksight

Two-tier image reading for text-only models in DeepSeek Harness: fast local OCR (RapidOCR, offline) first, then a vision model via modlens as fallback.

Updated 9/20/2026

dsh-gemini-multimodal

Gemini Multimodal

DeepSeek Harness plugin: multimodal tools (image/audio/video/document understanding, transcription, image generation) via Gemini API or the local Antigravity CLI.

Updated 9/20/2026✓ Scan passed

dsh-web-voice-input

Web Voice Input

Voice input for the DeepSeek Harness (DSH) Web GUI: a microphone button in the chat composer that records audio, transcribes it through an OpenAI-compatible Whisper API (Groq / OpenAI / SiliconFlow), and inserts the recognized text into the input box.

Updated 9/20/2026

Mimo Vision

DeepSeek Harness (DSH) native plugin: the describe_image tool, a vision bridge (image -> mimo-v2.5 -> text description) over the ctx.fs / ctx.credentials seams

Updated 9/20/2026

dsh-speech-plugin

Speech Plugin

Speech plugin for DeepSeek Harness: per-message speak button, composer voice input, and auto-announce toggle, over cloud TTS/ASR with Web Speech API fallback

Updated 9/20/2026

dsh-glm-vision

Glm Vision

GLM vision model plugin: registers the glm-vision provider route (glm-4.6v series, with image+text input declaration) and provides the glm_vision tool, allowing text-based primary models such as DeepSeek to directly call Zhipu vision models to analyze images.

Updated 9/20/2026

@muxiva/dsh-voice

Voice

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

Updated 9/20/2026

@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 9/20/2026

dsh-niulai-sound

Niulai Sound

牛来确认音 — DSH approval sound effects from the movie 《牛来》: plays 「妈妈」 when user confirmation is requested, interrupts it and plays 「牛来！」 the moment the user approves. 审批音效：请求确认时播放「妈妈」，批准瞬间掐断并播放「牛来！」。

Updated 9/20/2026

@launchmaniac/dsh-media-tools

Media Tools

OpenRouter image, video, and speech generation as dsh tools, shipped as an out-of-tree profile bundle

Updated 9/20/2026✓ Scan passed

← Previous 1 2 3 4 5…16 Next →

DeepSeek Harness Plugin Hub

Profiles Plugins Categories News Docs Sign in Manage Profiles

Profiles Plugins Categories News Docs Sign in