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-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 11/4/2026

dsh-boot-video

Boot Video

Add a video startup intro to DeepSeek Harness (DSH): includes an mp4, lets you import your own videos (codecs the browser cannot decode are automatically converted to H.264), name them, and switch between them at any time; fades into the interface when playback ends, with click or Esc to skip; every

↓ 658★ 0

Updated 11/4/2026

dsh-model-capability

Model Capability

Explicit model input-modality selection for the DeepSeek Harness Web UI

Updated 11/4/2026✓ 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 11/4/2026✓ Scan passed

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 11/4/2026✓ Scan passed

Imgpost

图邮 (imgpost): Let your DSH send and view images — local images, web images, AI image generation + image recognition (one eye), sent into the conversation with one click.

Updated 11/4/2026✓ Scan passed

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.

Updated 11/4/2026

@ljwei-stak/dsh-mv-cli

Mv Cli

Music video player for DeepSeek Harness Desktop: text, Canvas2D and WebGL2 3D scenes synced to your own audio. Sandboxed workshop packs can include licensed bilingual lyrics, timing and visual assets; only music is user-provided. Plugin code MIT; no song

Updated 11/4/2026✓ Scan passed

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 11/4/2026✓ Scan passed

dsh-deepseek-vision

Deepseek Vision

Out-of-tree dsh provider plugin: a DeepSeek gateway route that claims image input and transparently describes pasted images through a configured vision-language model (e.g. Qwen-VL) before the text-only DeepSeek wire sees them.

Updated 11/4/2026

@allmodels/dsh-speech

Speech

Speech-to-text and spoken answer summaries for DeepSeek Harness using AllModels.io.

Updated 11/4/2026✓ Scan passed

dsh-voice-talk

Voice Talk

Voice conversation mode for the DeepSeek Harness Web GUI: mic input with auto-submit, spoken readout of each reply's conclusion, and a hands-free multi-turn loop with barge-in.

Updated 11/4/2026✓ Scan passed

Mindseye

MindsEye: model-driven vision tools, structured evidence, and exact cache for DeepSeek Harness

Updated 11/4/2026

dsh-live2d-avatar

Live2d Avatar

A switchable Live2D avatar stage and desktop companion for DeepSeek Harness.

Updated 11/4/2026

dsh-voice-kit

Voice Kit

Voice input (Web Speech API) and read-aloud (speechSynthesis) for the DeepSeek Harness web GUI — DSH 语音输入 + 回复朗读套件

Updated 11/4/2026✓ Scan passed

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 11/4/2026✓ Scan passed

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 11/4/2026✓ Scan passed

@dsh-extension/dsh-vision-bridge

Vision Bridge

On-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

Updated 11/4/2026

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

Updated 11/4/2026

dsh-seedance2

Seedance2

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

Updated 11/4/2026✓ Scan passed

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 11/4/2026✓ Scan passed

@nutshelllee/dsh-voice-mode-desktop

Voice Mode Desktop

Full-duplex voice mode for DeepSeek Harness 0.2 desktop: streaming ASR to draft, sentence read-aloud, barge-in, live captions, plus an in-app settings page. An unofficial compatibility fork of dsh-voice-mode 0.7.15.

Updated 11/4/2026✓ Scan passed

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 11/4/2026✓ Scan passed

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 11/4/2026

dsh-subagent-vision

Subagent Vision

dsh bundle: subagent_vision — delegate image reading to a vision-capable model from a text-only session, plus paste-to-path so pasted images reach the subagent as file paths.

Updated 11/4/2026✓ Scan passed

gen-ai-pose-image

Gen Ai Pose Image

澜姿：从姿势线稿和衣装集给社区鲸鱼娘大肥鱼出图，也可装进 DeepSeek Harness。Lanpose generates images of the community whale-girl Dafeiyu from pose sketches and costumes, and installs into DeepSeek Harness.

Updated 11/3/2026

dsh-plugin-deepeye

Plugin Deepeye

DeepSeek Harness native plugin: vision capabilities for text-only LLMs (describe, OCR, VQA, layout analysis, clipboard)

Updated 11/4/2026

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 11/4/2026✓ Scan passed

deepseek-ivideo

Deepseek Ivideo

iPolloWork HyperFrames Video Studio and 27 editable video templates as a native DeepSeek Harness conversation view.

Updated 11/4/2026

@try-works/dsh-stt

Stt

Multi-model local speech-to-text for the DSH Web composer: Whistle and Voz, user-selectable, with lazy per-model download. Ships as a DSH bundle.

Updated 11/4/2026

← Previous 1 2 3 4 5 6…31 Next →

DeepSeek Harness Plugin Hub

Profiles Plugins Categories News Docs Sign in Manage Profiles

Profiles Plugins Categories News Docs Sign in