CATEGORY
Vision & Media DSH plugins
Verified manifests and exact versions in this category.
All plugins
377 pluginsdsh-native-image-viewerNative Image Viewer
Native zoom, pan, download, gallery, and region-note image viewer for DeepSeek Harness
dsh-conversation-shareConversation Share
Select a range of a DeepSeek Harness conversation and share it as a branded PNG long image, with draggable magnetically snapping range markers.
dsh-antv-avaAntv Ava
AntV AVA and GPT-Vis plugin for DeepSeek Harness: stream data-heavy answers as narrative text, charts, or both.
@achasoft/dsh-voiceVoice
Voice input for the DeepSeek Harness Web Client: a microphone control in the composer, a transcription capability seam, and two selectable providers
dsh-baidu-ocrBaidu Ocr
Baidu cloud OCR (PaddleOCR-VL + Unlimited-OCR) for DeepSeek Harness Web: drag images/PDFs in, OCR to markdown, write results as local files.
@blue/dsh-image-model-routerImage Model Router
DeepSeek Harness plugin: route an agent request to a vision model (deepseek-v4-flash-vision-exp) when the user message contains an image, and keep the original model otherwise.
dsh-agnesAgnes
Agnes AI image & video generation tools for DSH (agnes_image_generate / agnes_video_generate)
dsh-image-conatinerImage Conatiner
Codex-style generated-image gallery and lightbox for DeepSeek Harness
dsh-image-resizerImage Resizer
Resize oversized DSH Web conversation images before native attachment admission
vision-exp-tileVision Exp Tile
A large-image intelligent recognition plugin tailored for deepseek-v4-flash-vision-exp: whole-image precheck → local OCR + pixel grid (text) + proportional tiling around points of interest (longest edge 800) → aggregation; retains the whole-image 800x800 grid tiling mode. Does not count tokens or ca
dsh-screenshot-captureScreenshot Capture
Point-and-shoot screenshot capture for DeepSeek Harness: clipboard watcher + system floating window (comment & key-point, copy/save-doc/save-image) + instant OCR + Obsidian per-day merging + evening AI organization. 指哪拍哪 · 截图即存:剪贴板监听 + 鼠标位置系统级悬浮窗 + 即时 OCR + Obsidian 按天合并 + 晚间 AI 整理打双链
dsh-media-skillsMedia Skills
Free image reading (vision) and image generation skills for DeepSeek Harness (rc.7/rc.8/v0.1.1-rc.1) — GLM-4V-Flash free reading with DeepSeek-V4-Flash-Vision-Exp / SenseNova / Gemini failover, SiliconFlow Kolors for generation.
dsh-image-readImage Read
DeepSeek Harness plugin: structured image analysis via vision APIs (read_image_mimo tool) with Web UI config card. Cross-platform downscale/format conversion (optional sharp, sips fallback), cumulative payload budget, result caching. Attachment input moved to dsh-input-enhancement.
dsh-opencode-go-modelsOpencode Go Models
DSH plugin to sync opencode-go model catalog with precise multi-modal support
dsh-pdf-readerPdf Reader
AI-powered PDF reader for DeepSeek Harness with annotations, multi-PDF workflows, mixed image-text evidence, and on-demand OCR.
dsh-shotsShots
Shots tab for DeepSeek Harness: a video-player view (live + YouTube-style scrubber) over a browser daemon's screenshot feed in <workspace>/shots/
dsh-media-genMedia Gen
Generate images and videos in DSH chat via OpenAI-compatible providers configured in Model settings; dedicated Settings menu and workspace media_gen output.
dock-imagesDock Images
Image viewer for the dock file explorer: renders PNG, JPEG, GIF, WebP, BMP, SVG, ICO and AVIF files.
duhai-visionDuhai Vision
PaddleOCR-VL-first visual model adapter for Codex and DeepSeek Harness
jolly-dsh-visionJolly Dsh Vision
ModLens-style vision bridge for DeepSeek Harness: deepseek-v4-pro as the brain, deepseek-v4-flash-vision-exp as the eyes.
dsh-vision-anyVision Any
DeepSeek Harness vision plugin: paste images into text-only models and analyze them with any OpenAI-compatible, Anthropic, or Gemini vision API.
@oil-oil/dsh-visionVision
Near-native image understanding for text-only DeepSeek Harness models
@dsh-external/dsh-visionVisionalt · @dsh-external
DSH vision subagent plugin: delegates image recognition to the DeepSeek vision model
@harness-flow/dsh-voiceVoicealt · @harness-flow
dsh-voice — turn-based voice loop for DeepSeek Harness: pluggable Qwen / MiMo / local ASR+TTS engines, agent-driven speak/listen tools and browser PTT UI, built for interviewer presets
dsh-voice-input-spaceVoice Input Space
Voice input for DeepSeek Harness: hold Space in any editable field to speak, release to insert the transcript at the caret. Zero dependencies, browser Web Speech API. / 语音输入：在输入框长按空格键说话，松开自动上屏。零依赖，基于浏览器 Web Speech API。
dsh-imagegenImagegen
Provider-neutral image generation tool for DeepSeek Harness
@local/dsh-music-player-tuiMusic Player Tui
DSH TUI local music player: open a full-screen scene with /music, select a local directory, scan common audio formats (mp3/flac/m4a/ogg/wav...), play audio through the mpv/ffplay/afplay backends, loop a single track or playlist, delete tracks, and keep music playing uninterrupted when exiting the sc
@cabeta/dsh-image-themeImage Theme
Warp-inspired image-to-theme plugin for the DeepSeek Harness web client.
dsh-image-skinImage Skin
DSH web plugin: set a background image and adapt the theme colors (background + text + brand + borders) to the image palette.
@dsh-external/dsh-drop-to-pathDrop To Path
Drop or paste images, PDFs, office docs, zips, videos and audio into the DSH composer as workspace file paths instead of model attachments — lets a text-only model agent read them via vision tools.