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 11

CATEGORY

Vision & Media DSH plugins

Verified manifests and exact versions in this category.

All categoriesAgents & Orchestration1042Memory & Context1300Coding & Developer Tools2786UI & Customization3656Integrations & Communication1910Vision & Media615Search & Research865Security & Access1268Models & Usage1682Productivity & Workflow2234

All plugins

614 plugins
Lv0.1.0
@ycp424c/dsh-luna-vision-bridge

Luna Vision Bridge

DSH LLM adapter that transcribes native image attachments with Codex Luna before delegating to DeepSeek

vision-mediamodels-usage★ 1↓ 0
Updated 9/4/2026
v2.2.2
dsh-image-serve

Image Serve

Let AI assistants directly "see" local images in sessions: /ws/<absolute path> turns files anywhere on disk into same-origin HTTP URLs renderable in session Markdown. Show any local file in DSH web sessions — no staging directory, any drive.

vision-media★ 1↓ 0
Updated 9/4/2026
Tv1.1.1
dshtools-sensevoice-input

Tools Sensevoice Input

SenseVoiceSmall-powered local speech-to-text for the DSH Desktop input box: click the mic beside the composer, speak, and the recognized draft (with language/emotion tags) is written into the input.

vision-media★ 1↓ 0
Updated 9/3/2026
Cv0.1.0
dsh-computer-use-windows

Computer Use Windows

Windows Computer Use for DeepSeek Harness: window-bound screenshots, robust OCR, verified clicks, pure-OCR mode, pluggable vision models.

vision-media★ 1↓ 0
Updated 9/3/2026
Uv0.2.1
dsh-unlimited-ocr-skill

Unlimited Ocr Skill

Unlimited-OCR long-document parsing with a native DeepSeek Harness tool and GUI configuration.

vision-media★ 1↓ 0
Updated 9/2/2026
v0.2.4
dsh-media-serve

Media Serve

DeepSeek Harness host plugin: serves a configured workspace/media folder over the web server under /media, so any conversation can display local images by referencing http://<host>:<port>/media/<relative-path>.

vision-media★ 1↓ 0
Updated 9/2/2026
Av1.8.3
agnes-media

Agnes Media

Registers generate_image and generate_video tools for Agnes AI media models (agnes-image-2.1-flash, agnes-video-2.5-flash) in DeepSeek Harness. Supports multi-image reference via reference_image_urls.

vision-media★ 1↓ 0
Updated 9/2/2026
Vv0.2.0
dsh-vox-input

Vox Input

Voice (speech-to-text) input for the DSH Web composer via the browser Web Speech API — tap the mic, speak, the transcript fills the input box. Zero server, zero API keys, nothing leaves the machine. · DSH Web 语音输入：点麦克风说话，识别文字回填输入框（Chrome/Edge，无需 API key）。

vision-media★ 1↓ 0
Updated 9/1/2026
Pv6.1.0
dsh-ppt-master

Ppt Master

PPT Master skill for DeepSeek Harness: AI-driven presentation workflow for generating editable PPTX decks, SVG snapshots, native template filling, and PPTX enhancement.

productivity-workflowvision-media★ 1↓ 0
Updated 9/1/2026
Vv0.3.11
dsh-voco

Voco

DSH plugin dsh-voco

vision-media★ 1↓ 0
Updated 8/31/2026
Av0.1.0
dsh-anydoc-markdown

Anydoc Markdown

Converts documents (Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, PDF) to clean Markdown via the Rust firecrawl-anydoc crate and describes every embedded image with a vision model. Host plugin exposing a `convert_document` tool; the conversion + batched-vision engine is a bundled Python wra

productivity-workflowvision-media★ 1↓ 0
Updated 8/31/2026
Lv0.3.2
dsh-llm-vision

Llm Vision

Model-facing describe_image + extract_text tools for the DeepSeek Harness web GUI: gives a text-only model reliable image understanding and OCR through an OpenAI-compatible vision endpoint, with critical-inspection prompts, auto-preprocessing, retries, and a persistent answer cache.

vision-media★ 1↓ 0
Updated 8/31/2026
Tv0.1.0
dsh-tool-imagegen

Tool Imagegen

Text-to-image generation tool for DeepSeek Harness via OpenRouter's unified Image API, with capability-gated parameters and workspace file output

vision-media★ 1↓ 0
Updated 8/30/2026
Vv1.0.1
@difimim/dsh-voice-input

Voice Input

DeepSeek Harness voice input plugin: adds a microphone button to the input field and uses the browser Web Speech API to transcribe speech into text in real time.

vision-media★ 1↓ 0
Updated 8/30/2026
Sv0.1.0
dsh-screenshot-review

Screenshot Review

Screenshot review dsh skill: the model takes screenshots, reviews them, modifies the code, and iteratively improves the frontend.

ui-customizationdeveloper-toolsvision-media★ 1↓ 0
Updated 8/29/2026
Vv0.1.1
@lijian-ui/dsh-vision-toggle

Vision Toggle

Per-model vision (image input) toggle for DeepSeek Harness (dsh): list every configured model and flip a switch to enable/disable image support without hand-editing settings.yaml. 为 DeepSeek Harness 提供按模型的「支持图片」开关：无需手改 settings.yaml。

vision-mediamodels-usage★ 1↓ 0
Updated 8/28/2026
v0.3.5
dsh-periscope

Periscope

DSH Desktop plugin: keep text-only models (deepseek-v4-flash / deepseek-v4-pro) as the session default and automatically route image-bearing requests to a configured vision model; also ships the generic file-attachment feature (drag/paste any file as a durable attachment the agent reads by path) as

vision-media★ 1↓ 0
Updated 8/27/2026
v0.1.1
dsh-video-player

Video Player

Floating, draggable, resizable video scene player for DeepSeek Harness. Plays scene-per-MP4 clips from a Stash-style scene server, plus best-effort YouTube / Twitch / Jellyfin / custom links.

vision-mediaui-customization★ 1↓ 0
Updated 8/25/2026
Pv0.1.0
phone-eye

Phone Eye

Let your AI agent see and operate a real Android phone — vision + UI-tree fusion over adb, for any MCP client

integrations-communicationvision-media★ 1↓ 0
Updated 8/25/2026
Vv0.3.1
dsh-voice-input

Voice Inputalt · lhenlihai-hub

Voice dictation and transcript cleanup for DeepSeek Harness, using the current session model.

vision-media★ 1↓ 0
Updated 8/25/2026
Vv0.1.0
@hackerfish/dsh-voice-input

Voice Inputalt · @hackerfish

Voice input: microphone button in the dialog, browser-built-in Web Speech API (zh-CN) recognition, results inserted into the input field draft

vision-media★ 1↓ 0
Updated 8/24/2026
Dv0.1.0
dsh-deepseek-model-router

Deepseek Model Router

Auto-switch DeepSeek models for DeepSeek Harness: routes every model request to the vision model when images are present, to the pro model for complex tasks, and to the fast model otherwise; includes a switch_model tool for manual per-session overrides.

models-usagevision-media★ 1↓ 0
Updated 8/24/2026
v0.3.0
dsh-funasr-voice

Funasr Voice

DSH Web local offline voice input plugin: the browser captures microphone audio → host launches local FunASR (SenseVoiceSmall) for recognition → text is entered into the input field.

vision-media★ 1↓ 0
Updated 8/23/2026
Iv1.0.0
dsh-imggen

Imggen

DeepSeek Harness plugin: text-to-image output with in-chat image cards, download button, history gallery, and provider selection tabs

vision-media★ 1↓ 0
Updated 8/22/2026
v0.1.0
dsh-attachment-downscale

Attachment Downscale

Automatic attachment fallback: DSH image limits (one side ≤2000px / ≤3.5MB / ≤40 million pixels) no longer reject oversized images; sharp automatically resizes or re-encodes them before storage, so original phone photos can be uploaded without exceeding limits.

vision-media★ 1↓ 0
Updated 8/22/2026
v0.1.3
dsh-text2img-compress

Text2img Compress

把长文本渲染成图片发送来压缩 LLM 输入 token（DeepSeek 视觉模型、每图 384 token 封顶）— text-as-image token compression for DeepSeek Harness

vision-mediamodels-usage★ 1↓ 0
Updated 8/22/2026
Cv0.1.1
dsh-computer-use-vision

Computer Use Vision

Windows computer-use capability for DeepSeek Harness: screenshot → vision model → simulated mouse/keyboard input, with self-evolving knowledge base.

vision-media★ 1↓ 0
Updated 8/22/2026
Gv1.0.0
@dsh-extension/dsh-generation-image

Generation Image

On-demand image generation for DeepSeek Harness (DSH): a generate_image tool that calls your own OpenAI-compatible image URL + API key and delivers the image into the session

vision-media★ 1↓ 0
Updated 8/22/2026
Iv0.1.2
dsh-image-vision-bridge

Image Vision Bridge

DSH host plugin: automatically sends images in user messages to a vision model (default mimo-v2.5 on opencode-go) and feeds the returned text description to the main text model (e.g. deepseek-v4-pro), without touching the visible chat transcript.

vision-mediamodels-usage★ 1↓ 0
Updated 8/22/2026
Iv0.1.0
@dsh-external/dsh-image-tiler

Image Tiler

DSH agent tool: slice a large image into labeled ~800x800 tiles plus an overview thumbnail, preserving detail for vision models.

vision-media★ 1↓ 0
Updated 8/21/2026
← Previous1…910111213…21Next →
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in