Vision

September 22, 2026 · View on GitHub

Image understanding for text-only models.

476 entries, most-starred first. Back to the registry README · gallery.

NameRepo ★RepoDescriptionVerified against
archify69385tt-a1i/archify · npmOpt-in DeepSeek Harness Skill-only bundle for the Archify architecture-diagram skill.0.1.0-rc.8 (2026-08-20)
modlens ⭐4011liustack/modlens · npmVision plugin for text-only models: image understanding bridged into the harness via a dsh.bundle patch layer, shipping a modlens skill alongside0.1.0-rc.8 (2026-08-20)
dsh-vision-router1115ysr666/dsh-vision-router · npmTurn-level vision routing with provider fallbacks, a cached vision_describe tool, JSON output, and optional per-host proxy.0.1.0-rc.8 (2026-08-20)
dsh-vision-toolkit884Anionex/dsh-vision-toolkit · npmHarness-native integration of agent-vision-toolkit for text-only models: image Q&A with intent, long-screenshot OCR, UI restoration, grounding, and pixel diff0.1.0-rc.8 (2026-08-20)
deepseek-harness-android-app274woaiys3/deepseek-harness-android-appModel-facing Android system tools (package/app/setting/screenshot/input) over Shizuku shell.unverified
dsh-video-lens114dundunhan/dsh-video-lens · npmGive text-only DeepSeek Harness agents video understanding: scene-aware frame sampling + VLM + optional ASR transcript fused into timeline evidence. / 给纯文本模型的视频理解插件（场景感知抽帧 + VLM + 可选语音转录）0.1.0-rc.8 (2026-08-20)
dsh-vision-oil88oil-oil/dsh-visionNear-native image understanding for text-only DeepSeek Harness models.0.1.0-rc.8 (2026-08-20)
dsh-imagegen83dickpy/dsh-imagegen · npmAI 生图 (image generation) plugin for the dsh web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint (gpt-image-2 / gpt-image-1 / dall-e-3), with a settings card0.1.0-rc.8 (2026-08-20)
beautiCode82starsstreaming/beautiCodeCordis plugin: image/video backgrounds for DeepSeek Harness web.0.1.0-rc.8 (2026-08-20)
picturereader36jing-hy/picturereader · npmDSH plugin: pixel-to-text image reading for text-only models. Downscales and color-quantizes PNG/JPEG/GIF/BMP and feeds the coarse pixel grid to the model so DeepSeek can 'see' layout, colors and0.1.0-rc.8 (2026-08-20)
deepseek-harness-docker19AlliotTech/deepseek-harness-dockerReproducible container image for DeepSeek Harness0.1.0-rc.8 (2026-08-20)
deepseek-visionary17xlight/deepseek-visionary · npmDeepSeek Visionary native plugin for DeepSeek Harness: deepseek_vision / status / login / logout native tools backed by the visionary-server CLI (DeepSeek web vision model, no API key).0.1.0-rc.8 (2026-08-20)
dsh-media-skills-mjorgin17MJorgin/dsh-media-skillsFree image reading (vision) and image generation skills for DeepSeek Harness — Zhipu GLM-4V-Flash (Google Gemini optional) for reading, SiliconFlow Kolors for generation.0.1.0-rc.8 (2026-08-20)
dsh-visual-plugin16jyh20030112/dsh-visual-pluginVision bridge plugin for DeepSeek Harness: when the main model has no vision, forward user images to a configurable OpenAI-compatible vision model and show results in a Web UI right panel. Host.0.1.0-rc.8 (2026-08-20)
dsh-vision-proxy14Flyvhidbwo/dsh-vision-proxy · npmdeepseek-vision provider route that transcribes attached images via an OpenAI-compatible VLM before DeepSeek answers.0.1.0-rc.8 (2026-08-20)
dsh-codex-oauth-wnjxyk13WNJXYK/dsh-codex-oauth · npmUnified OpenAI Codex subscription plugin for DeepSeek Harness: GPT models, OAuth, quota, image generation, and web search.0.1.0-rc.8 (2026-08-20)
dsh-diagram13hanzhangzzz/dsh-diagram · npmTurn articles in DeepSeek Harness into editable Excalidraw canvases0.1.0-rc.8 (2026-08-20)
dsh-ocr-plugin13CraZY222123/dsh-ocr-pluginLocal OCR provider (rapidocr fast + DeepSeek-OCR-2 deep) registered as the 'ocr' service for the llm-deepseek adapter seam. Unofficial community plugin for DeepSeek Harness.unverified
dsh-vision-opencode13poiuyjie/dsh-vision-opencodeDeepSeek Harness plugin: configurable vision model with vision_read_image tool, composer-bar vision-model selector, and automatic image-to-text conversion for text-only main models.0.1.0-rc.8 (2026-08-20)
vision-exp-tile12Nicholas023/vision-exp-tile为 deepseek-v4-flash-vision-exp 量身定制的大图智能识图插件：整图预检 → 本地 OCR+像素网格（文字）+ 兴趣点按比例切块（最长边 800）→ 汇总；保留全图 800x800 网格切块模式。不统计 token、不计算费用。v0.4.1：慢机测试自适应（设备档位/可配置OCR池超时/设置页跳过声明/自检入口/安装即优化）。0.1.0-rc.8 (2026-08-24)
dsh-file-upload-a903067211a903067276-rgb/dsh-file-uploadUpload button + drag-and-drop files into DSH conversation as local paths (works with any vision plugin)0.1.0-rc.8 (2026-08-20)
dsh-mermaid-mrmolabs11MrmoLabs/dsh-mermaidRender Mermaid code blocks in DeepSeek Harness with a diagram/code toggle.0.1.0-rc.8 (2026-08-25)
dsh-web-file-uploader11Mooling0602/dsh-web-file-uploaderA DeepSeek-style paperclip attach button in the DSH web composer; uploads files to the DSH host (model-aware: native image blocks for multimodal models, file paths for text-only models).0.1.0-rc.8 (2026-08-20)
dsh-auxiliary-dshplugi10dsh-plugins/dsh-auxiliary · npmDeepSeek Harness plugin that uses configured model providers for image analysis and context compaction.0.1.0-rc.8 (2026-08-20)
dsh-mmx-bridge10welsione/dsh-mmx-bridgeMiniMax multimodal bridge for DeepSeek Harness (DSH). One mmx_bridge tool covers describe/image/video/speech/music/cover/search/quota; optional web_search/read_image takeover; built-in client0.1.0-rc.8 (2026-08-20)
dsh-origin-plugin10Fantasality/dsh-origin-pluginDrive Origin scientific plotting from DeepSeek Harness AI chat via MCP - 28 tools, styled multi-series plots, inline image preview, statistics batch (t/ANOVA/PCA/survival), stable error codes.0.1.1-rc.2 (2026-09-09)
dsh-roleplay10chinosk6/dsh-roleplay · npmRole-play conversations, character-card authoring and image generation for DeepSeek Harness0.1.0-rc.8 (2026-08-20)
dsh-deepseek-vision-siegfly9siegfly/dsh-deepseek-vision · npmOut-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 the0.1.0-rc.8 (2026-08-20)
dsh-qwen38-local-qol9Yunado/dsh-qwen38-local-qolDeepSeek Harness QoL plugin for the local Qwen3.8 line (27B, Flash-Next): per-request thinking budgets on both llama.cpp and NInfer dialects, vision + tools, and a compaction backend whose summaries0.1.1-rc.2 (2026-09-18)
dsh-vision-linenxi9linenxi-ctrl/dsh-vision · npmExternal vision model for DeepSeek Harness: config panel, send-image recognition, and screenshot tools.0.1.0-rc.8 (2026-08-20)
dsh-chat-imagine8corrinehu/dsh-chat-imagineGenerate images via API (image models filtered from those already set up in DSH) or local CLIs (MiniMax mmx), probe available backends, and display images inline in the chat.0.1.0-rc.8 (2026-08-20)
dsh-free-vision8FuzzySoul/dsh-free-vision · npmFree vision plugin for DeepSeek Harness (dsh): image understanding for text-only models with free-tier providers (Qwen3-VL-Flash / DeepSeek-OCR / Doubao). 免费视觉插件：纯文本模型看图能力，优先免费模型（通义千问 / 硅基流动 / 豆包）。0.1.0-rc.8 (2026-08-20)
dsh-highres-vision8azwosile/dsh-highres-visionDeepSeek Harness vision enhancer: raises image limits to official values and provides high-resolution tiled image reading via a dedicated tool.0.1.0-rc.8 (2026-08-25)
dsh-windows-ocr8maxwell-feng/dsh-windows-ocr · npmdsh plugin: recognize attached images with the built-in Windows OCR engine (Windows.Media.Ocr) and send only the recognized text to the model — image bytes never leave the machine.0.1.0-rc.8 (2026-08-20)
image-vision8wangyang10/image-vision · npmDeepSeek Harness plugin: gives text-only models (e.g. DeepSeek) image-reading ability via any OpenAI-compatible vision API. Registers the vision_query tool, DSH credentials integration, and theunverified
deepseekeyes7dttxorg/deepseekeyes · npmAuditable vision and cross-platform Computer Use runtime for DeepSeek Harness with source-preserving evidence.0.1.0-rc.8 (2026-08-20)
dsh-mimo-agent-tools7ch1bug/dsh-mimo-agent-toolsXiaomi MiMo search + multimodal tools for DSH agents: mimo_search/vision/audio/video/asr/tts.0.1.0-rc.8 (2026-08-20)
dsh-browser-ben7am1n6ben7am1n/dsh-browser · npmBrowser automation for DeepSeek Harness: Playwright-powered open/click/type/screenshot/eval tools so the agent can drive real web pages.0.1.0-rc.8 (2026-08-20)
dsh-minimal-vision6Flora233333/dsh-minimal-visionLightweight vision assist preset and CLI for DeepSeek Harness.0.1.0-rc.8 (2026-08-20)
dsh-vision-bridge-sfyyy6sfyyy/dsh-vision-bridge · npmOn-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model0.1.0-rc.8 (2026-08-20)
dsh-guide-dog5AtropinolTT/dsh-guide-dogGuide Dog for DSH, powered by MiniMax — multimodal plugin: image/video/music/speech generation, vision inspection tools, voice mode, microphone voice input and real-time voice call mode.0.1.1-rc.2 (2026-09-09)
dsh-image-bridge-kbpoyo5kbpoyo/dsh-image-bridge · npmDSH Web plugin that lets text-only models see images: paste images in the chat and send without file paths; the model discovers its own vision tools. Multimodal models pass through natively.0.1.0-rc.8 (2026-08-20)
dsh-local-llm-controller5Lbunc/dsh-local-llm-controllerDSH plugin: start/stop a local llama.cpp llama-server from the settings → plugins page — two model slots (A/B) with per-slot model-file selection, eight editable launch-parameter groups (text/vision0.1.0-rc.8 (2026-08-25)
dsh-ocr-local5balcoz/dsh-ocr-localLocal OCR for DeepSeek Harness: paste/attach an image, get its text via PP-OCRv5 + ONNX Runtime, fully offline. TUI (cc-tui) and Web. / DeepSeek Harness 本地 OCR 插件：图片转文字，PP-OCRv5 + ONNX Runtime，完全离线0.1.0-rc.8 (2026-08-20)
dsh-ocr-local-grelvan5grelvan/dsh-ocr-localLocal OCR fallback for DeepSeek Harness (Web): when the routed model cannot accept image input, a pasted image is saved locally and its text read by PP-OCRv5 + ONNX Runtime — fully offline, no vision0.1.1-rc.2 (2026-09-18)
dsh-plugin-appshot5TaurusWood/dsh-plugin-appshot · npmdsh-plugin-appshot — a DeepSeek Harness plugin for macOS context screenshot capture.0.1.0-rc.8 (2026-08-20)
dsh-plugin-describe-image5whitelonng/dsh-plugin-describe-imageModel-facing describe_image tool: asks a vision-language model at an OpenAI-compatible endpoint to describe an image file or URLunverified
dsh-prism5YOGEMOW/DeepSeek_PrismDeepSeek Prism 仓库根：Codex Skill 与 DeepSeek Harness 插件双包发布unverified
dsh-tool-see-image5gugu123a/dsh-tool-see-image · npmsee_image tool for DSH: route image files to a configurable vision model (OpenAI-compatible API) and relay its description back to a text-only model0.1.1-rc.2 (2026-09-04)
deepseek-harness-desktop-kevph2024KevPH2026/deepseek-harness-desktopA native macOS desktop experience for DeepSeek Harness — multimodal generation, community plugin discovery, safe updates, and bilingual docs.0.1.0-rc.8 (2026-08-20)
DeepSeek-harness-wecom4sliverp/DeepSeek-harness-wecomWeCom AI Bot text, image, and file channel bridge for DeepSeek Harness0.1.0-rc.8 (2026-08-20)
dock-images4AKS1st/dock-imagesImage viewer for the dock file explorer: renders PNG, JPEG, GIF, WebP, BMP, SVG, ICO and AVIF files.0.1.0-rc.8 (2026-08-20)
ds-vision-plugin4Sorwcyra/ds-vision-pluginAutomatic Web image-to-text bridge plus vision and OCR tools for DeepSeek Harness0.1.0-rc.8 (2026-08-20)
dsh-codex-tools4SPYQWER1/dsh-codex-tools · npmCodex-backed web search, image generation, and image understanding tools for the DeepSeek Harness.0.1.0-rc.8 (2026-08-20)
dsh-computer-use-xiaoheiz4xiaoheizi1212/dsh-computer-useModel-agnostic Computer Use capability for DeepSeek Harness: isolated browser first, provider-neutral observation, text planner + third-party vision perception.0.1.0-rc.8 (2026-08-20)
dsh-custom-provider-settings4supersealwqas/dsh-custom-provider-settingsRequest headers, image input, and reasoning settings for custom DeepSeek Harness providers0.1.0-rc.8 (2026-08-20)
dsh-image-pathify4dami9527/dsh-image-pathify · npmDeepSeek Harness plugin: let text-only models receive pasted images, and analyze them with a built-in OpenAI-compatible vision tool0.1.0-rc.8 (2026-08-20)
dsh-image-preview-algerkon4algerkong/dsh-image-previewImage preview in the dsh session: read_image tool results render as a small thumbnail by default and open full-size in the built-in lightbox on click0.1.1-rc.2 (2026-08-28)
dsh-image-subagent4yuqingsh/dsh-image-subagent让纯文本主模型（DeepSeek V4 等）也能接收图片附件：图片投影为显式占位文本，由主模型委托视觉子代理经 read_attachment/read_image 读取。零核心补丁，纯插件实现。0.1.0-rc.8 (2026-08-20)
dsh-model-router-superboy9114superboy911/dsh-model-routerThin routing policy for DeepSeek Harness: keyword routing, allowlisted model switching, and isolated image generation. / DeepSeek Harness 薄路由策略：关键词路由、白名单模型切换和隔离生图。0.1.0-rc.8 (2026-08-20)
dsh-plugin-vision-tdf19954tdf1995/dsh-plugin-visionDeepSeek Harness native plugin: give text-only LLMs (e.g. DeepSeek) vision via free Gemini / GLM vision APIs — describe images, OCR, VQA, screenshots, charts; integrated browser paste & drop.0.1.0-rc.8 (2026-08-20)
dsh-qwen-mm-plugins4ShuiHan268/dsh-qwen-mm-pluginsQwen-MM multimodal tools for DeepSeek Harness: vision, OCR, grounding, ASR, and a web settings page for the API key.0.1.0-rc.8 (2026-08-20)
dsh-tesseract-ocr4maxwell-feng/dsh-tesseract-ocr · npmdsh 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.0.1.0-rc.8 (2026-08-20)
dsh-tool-ocr4ferstar/dsh-tool-ocr · npmStandalone OCR tool plugin for DeepSeek Harness: local image text recognition (nbocr / PP-OCRv6) for models without vision.0.1.0-rc.8 (2026-08-20)
dsh-ugui-preset4BaronCyrus/dsh-ugui-presetPreset-scoped multi-Canvas uGUI Workspace with a standalone-only browser designer, extended selectable, scrolling, masking and layout components, stable node IDs, safe gesture undo, image staging0.1.0-rc.8 (2026-08-20)
dsh-vision-bridge4GXX182/dsh-vision-bridge · npmDeepSeek Harness plugin that bridges images to external vision APIs and returns text-only analysis0.1.0-rc.8 (2026-08-20)
dsh-vision-hub4xing666173/dsh-vision-hub为 dsh-tool-vision 桥接导出的图片提供对话内联预览:用户粘贴的图片在气泡中显示缩略图,不改变桥接文本与模型行为unverified
dsh-vision-sidecar4121103qwq/dsh-vision-sidecarAdd no-key hosted or OpenAI-compatible vision to DeepSeek Harness while keeping the configured reasoning model0.1.0-rc.8 (2026-08-20)
improved_vision_for_deepseek4zyh20041227/improved_vision_for_deepseekLoss-aware, full-coverage image tiling for DeepSeek Harness vision models0.1.0-rc.8 (2026-08-24)
Tripo3D-Plugin-dsh4VAST-AI-Research/Tripo3D-Plugin-dshTripo 3D skills for DeepSeek Harness — generate engine-ready 3D assets from a text prompt or a reference image via tripo-cli, with texturing, rigging, retopology and format conversion in one pass.0.1.1-rc.2 (2026-09-18)
dsh-agent-router3peterwangze/dsh-agent-routerDeepSeek Harness multi-model routing plugin: route tasks to custom specialist agents (vision / image generation / translation / speech / subagent) with per-agent providers & models, multimodal0.1.0-rc.8 (2026-08-20)
dsh-aux-vision3XyTT2N2bTc/dsh-aux-visionDeepSeek Harness 辅助视觉插件：任意纯文本主模型 + 任意视觉模型（默认 opencode-go/mimo-v2.5）。含图轮次自动让视觉模型看原图（像素级），并把描述以文本注入当前轮供主模型使用；纯文本轮零视觉调用。0.1.0-rc.8 (2026-08-20)
dsh-computer-use-plugin3beijingwahw/dsh-computer-use-pluginVision-only desktop automation plugin for DeepSeek Harness (fusion refactor)0.1.1-rc.2 (2026-09-18)
dsh-desktop-puddingf3puddingfish/dsh-desktopDSH 图像理解插件：接管 describe_image 工具，后端为本地 mmx CLI（MiniMax VLM）；本机无 mmx 时自动静默休眠（不注册工具、不显示配置、零报错）。支持本地路径 / http(s) URL / 附件引用；含输入框图片按钮（附件上传路由 + 发送改写 + 会话内缩略图预览）与设置卡片。移植自0.1.0-rc.8 (2026-08-20)
dsh-docker-devlythe3devLythen/dsh-dockerDocker image for DeepSeek Harness, with self-hosted deployment supportedunverified
dsh-focus-overlay3boogoo619/dsh-focus-overlay · npmFocus Mode for the dsh web GUI: a full-screen reading overlay that hides chrome and folds the AI tool-call flow into summaries, reusing the official Markdown / image primitives.0.1.0-rc.8 (2026-08-20)
dsh-her-eyes3huashenglian/dsh-her-eyesApplication-level Vision-Language-Model (VLM) analyzer for DeepSeek Harness: analyze_image tool with primary/backup OpenAI-compatible endpoints, automatic failover, and an auto-saving web settings0.1.0-rc.8 (2026-08-20)
dsh-image-gen3LeemanCheung/dsh-image-genGPT Image 2 generation with progressive Codex-style previews for DeepSeek Harness0.1.0-rc.8 (2026-08-20)
dsh-image-transcription-plugin3kutcr/dsh-image-transcription-pluginImage transcription capability and LLM provider for DeepSeek Harnessunverified
dsh-imggenerate3Bald0Wang/dsh-imggenerateImage-generation tool plugin for DeepSeek Harness: qwen-image-3.0 (Aliyun MaaS) and doubao-seedream (Volcano Ark) providers0.1.0-rc.8 (2026-08-20)
dsh-llm-vision-bridge3Einskyle/dsh-llm-vision-bridge · npmRoute image attachments to a vision model and return results to the dsh web GUI.0.1.0-rc.8 (2026-08-20)
dsh-multimodal3MC5lan/dsh-multimodalMultimodal eyes and hands for DeepSeek Harness: GLM vision transcription, OCR, and text-to-image via DashScope / OpenAI-compatible backends, with an in-conversation generated-image card.0.1.0-rc.8 (2026-08-20)
dsh-multimodal-chenkezh3chenkezhen480/dsh-multimodalImage recognition and image generation for DeepSeek Harness: model-facing tools that call any OpenAI-compatible external API (vision chat/completions and images/generations), with no built-in model0.1.0-rc.8 (2026-08-20)
dsh-omni-workstation3huashenglian/dsh-omni-workstationOmni-modal workstation plugin for DeepSeek Harness: analyze_image + 6 vision toolkit tools (zoom/sample_colors/image_diff/ocr/detect/show), generate_image, and generate_video (t2v/i2v async-task).0.1.1-rc.2 (2026-09-18)
dsh-open-file3hyper-dsh-plugins/dsh-open-file · npmWorkspace-bound arbitrary file upload, reading, OCR, and rendering for DeepSeek Harness.0.1.0-rc.8 (2026-08-20)
dsh-pdf-reader-angelosz3AngelosZou/dsh-pdf-readerDeepSeek Harness plugin: content-aware PDF reading tools for vision models (pdf_scan / pdf_read_page / pdf_render_region). Detects figures (vector+raster), tables, math, and two-column layout per0.1.1-rc.2 (2026-08-26)
dsh-plugin-deepeye3Favio8/dsh-plugin-deepeye · npmDeepSeek Harness native plugin: vision capabilities for text-only LLMs (describe, OCR, VQA, layout analysis, clipboard)0.1.0-rc.8 (2026-08-20)
dsh-plugin-muapi3SamurAIGPT/dsh-plugin-muapiDeepSeek Harness plugin that exposes MuApi's 100+ image, video, and audio generation models as an agent tool.0.1.0-rc.8 (2026-08-20)
dsh-plugin-multimodal3shinjiyu/dsh-plugin-multimodalVision sidecar for DeepSeek Harness: accept image attachments on text-only models, describe them, then send text to the main model.0.1.0-rc.8 (2026-08-20)
dsh-plugin-vision-bridge-cling3c-ling/dsh-plugin-vision-bridgeVision bridge for the DeepSeek Harness web GUI: upload/paste images into a chat, describe them through an OpenAI-compatible vision API, and feed English text descriptions to text-only models.0.1.0-rc.8 (2026-08-20)
dsh-sfversion3sparkmio/dsh-sfversionStepFun 视觉桥(step-3.7-flash):给纯文本模型装上眼睛——图片描述 + UI 还原,原生图片消息自动翻译0.1.0-rc.8 (2026-08-20)
dsh-vision-mix3haiziyao/dsh-vision-mix · npmA DeepSeek Harness Mix plugin for vision routing plus GPT Image generation and editing.0.1.0-rc.8 (2026-08-20)
dsh-vision-plugin-agents363Agents365-ai/dsh-vision-pluginImage understanding for text-only models via OpenRouter free vision models0.1.0-rc.8 (2026-08-20)
dsh-vision-plugin-nexsjour3nexsjournal/dsh-vision-pluginDeepSeek Harness plugin: (1) installs an image-input (input modalities) checkbox into the Models settings catalog so a custom model can declare input:[text,image] and DSH passes images straight to it0.1.0-rc.8 (2026-08-20)
dsh-vision-provider3libinyam/dsh-vision-providerDeepSeek Harness adapter that exposes each configured vision model as a selectable DeepSeek composite in Web UI.0.1.0-rc.8 (2026-08-20)
dsh-vision-terry12138qy3Terry12138qy/dsh-visionVision tool for text-only DeepSeek models: send images to Qwen or GLM multimodal and return descriptions.0.1.0-rc.8 (2026-08-20)
dsh-webbridge-bill91093bill9109/dsh-webbridgeKimi WebBridge host plugin for DeepSeek Harness: model tools that drive the user's REAL browser (navigate, snapshot, click, fill, evaluate, screenshot, network inspection, tab management) through the0.1.0-rc.8 (2026-08-20)
dsh-wechat-bridge-kairos093Kairos0922/dsh-wechat-bridgeWeChat ⇄ DSH bridge bundle: iLink gateway + conversation node with dynamic agent-preset routing, image-in-session, and a Web settings panel0.1.0-rc.8 (2026-08-20)
dsh-wechat-mp-studio3FuncWei/dsh-wechat-mp-studioWeChat Official Account content studio for DeepSeek Harness: anti-homogenization writing methodology, blessing-image visual baseline, gpt-image cover pipeline with OCR acceptance, interaction rules0.1.0-rc.8 (2026-08-20)
meow-vision3meimiaoji-creator/meow-visiondsh 插件：给文本模型补一双眼睛 + 给多模态模型补一对观察 UI 渲染的眼睛 —— 设置弹窗选视觉模型 + meow_vision 工具 + meow_preview 组件截图工具0.1.0-rc.8 (2026-08-21)
multimodal-bridge3Spirit4471/multimodal-bridge · npmDeepSeek Harness plugin bundle: qwen_vision (Qwen-VL image understanding) and qwen_generate (Qwen-Image text-to-image) tools for text-only models0.1.0-rc.8 (2026-08-20)
phone-eye3boheastill/phone-eyeLet your AI agent see and operate a real Android phone — vision + UI-tree fusion over adb, for any MCP client0.1.1-rc.2 (2026-08-26)
screenshot-feedback-hook-mcp3lkh081231/screenshot-feedback-hook-mcpScreenshot feedback for DeepSeek Harness — let your coding agent SEE what it builds0.1.0-rc.8 (2026-08-24)
visual-review3wang-bool/visual-review · npmDSH plugin: renders images inline in DeepSeek Harness Web chat and gives text-only models vision — cloud multimodal API first, local Qwen3-VL fallback.0.1.0-rc.8 (2026-08-20)
wavespeed-dsh-skill3WaveSpeedAI/wavespeed-dsh-skillWaveSpeed skill for DeepSeek Harness (dsh): generate and edit AI media (image, video, audio, 3D) via the open-source wavespeed CLI.0.1.0-rc.8 (2026-08-20)
agnes-media2LittleBeaverStudio/agnes-mediaRegisters generate_image and generate_video tools for Agnes AI media models (agnes-image-2.1-flash, agnes-video-v2.0) in DeepSeek Harness.0.1.0-rc.8 (2026-08-20)
DeepSeek-Harness-linux-2MoneShadow/DeepSeek-Harness-linux-Vision assist for DeepSeek Harness: lets the main model see images through an OpenAI-compatible vision API0.1.0-rc.8 (2026-08-20)
dsh-anydoc-markdown2SeerableOfficial/dsh-anydoc-markdownConverts 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. Host0.1.1-rc.2 (2026-09-01)
dsh-bg-image2lyh9712/dsh-bg-imageDSH Web 背景图插件（成品版，带设置界面）：选图/填 URL/本地图片/透明度/模糊度，设置持久化在浏览器 localStorage0.1.0-rc.8 (2026-08-20)
dsh-Bio-image-dup-check2PetCT/dsh-Bio-image-dup-check生命科学科研图片查重：整图重复/翻转/旋转/缩放 + 单图内局部复制粘贴(copy-move)检测，本地离线，输出美观报告。0.1.1-rc.2 (2026-08-26)
dsh-capture2Max-Null/dsh-captureSSiD (思灵) quick screenshot capture: tray/hotkey → fullscreen box-select overlay → cropped image into the current conversation composer0.1.0-rc.8 (2026-08-25)
dsh-chat-image-lightbox2loyalchiiina/dsh-chat-image-lightboxDSH plugin: display images inline in chat with lightbox zoom, download (save-as), and prev/next navigation0.1.0-rc.8 (2026-08-25)
dsh-cliproxyapi-provider2ChadCSong/dsh-cliproxyapi-providerCLIProxyAPI provider for DeepSeek Harness with local auto-discovery, dynamic model sync, model switching, and vision preprocessing.0.1.0-rc.8 (2026-08-20)
DSH-CODEX-SUBSCRIPTION-POOL2Eve-146T/DSH-CODEX-SUBSCRIPTION-POOLDeepSeek Harness plugin for multi-account OpenAI Codex OAuth, usage, web search, and image generation0.1.0-rc.8 (2026-08-20)
dsh-conversation-share-bill91092bill9109/dsh-conversation-shareSelect a range of a DeepSeek Harness conversation and share it as a branded PNG long image, with draggable magnetically snapping range markers.0.1.0-rc.8 (2026-08-20)
DSH-dseyes2Okkay712/DSH-dseyes · npmGive DeepSeek Harness free eyes — natively. Paste or drop an image into the Web GUI composer: it appears as a thumbnail attachment (like a normal AI chat), and before the text-only DeepSeek model is0.1.0-rc.8 (2026-08-20)
dsh-filelens2Han-Yao94/dsh-filelensFileLens — right-column file explorer for DeepSeek Harness: lazy directory tree, multi-format preview (Markdown/JSON/CSV/diff/log/hex/image), search & grep, tabs, inline editing with containment + ver0.1.0-rc.8 (2026-08-20)
dsh-frosted-window2SenryLee/dsh-frosted-windowUpload an image as a full-window frosted-glass theme for DeepSeek Harness Web. Official Light / Dark / System stay in charge.0.1.0-rc.8 (2026-08-20)
dsh-image-inline2condaThinker/dsh-image-inlineshow_image tool that renders a local image inline in the web chat without putting pixels into model context.0.1.0-rc.8 (2026-08-20)
dsh-image-plugins2alanzhao0128/dsh-image-plugins · npmMultimodal plugin for DeepSeek Harness: understand images and generate images through configurable OpenAI-compatible or DashScope endpoints.0.1.0-rc.8 (2026-08-20)
dsh-image-reader2zcXie777/dsh-image-readerGive DeepSeek Harness agents the ability to read images directly: a model-facing read_image tool that answers questions about an image through any OpenAI-compatible vision endpoint.0.1.0-rc.8 (2026-08-20)
dsh-image-to-path2cesaryike/dsh-image-to-pathLet DSH text-only-model conversations accept dragged/pasted images: save them into the session workspace and insert the file path as text, bypassing the webui attachment channel that otherwise0.1.0-rc.8 (2026-08-20)
dsh-image-tools2xiaoxianyu-office/dsh-image-toolsChat-image bridge, read_image deny, and conversational image_recognize for text-only DeepSeek Harness models.0.1.0-rc.8 (2026-08-20)
dsh-image-vision-xiaoyuin2xiaoyuink/dsh-image-vision图片识别插件：自动判断当前模型是否具备视觉能力，有则用当前模型并按插件预设提示词分析，无则调用插件配置的视觉模型。文本模型可直接在对话框粘贴/上传/拖拽图片，发送时自动写入 DSH 附件存储（永久），消息区渲染缩略图，模型自动调用 image_vision / ocr / ground / crop 系列工具识别与精读；模型选择器保持简洁。0.1.0-rc.8 (2026-08-20)
dsh-inline-images23403473060/dsh-inline-images对话内联图片:LLM 回复中输出的本地图片路径直接在消息正文内渲染为图片,支持 9 种格式、点击放大灯箱、可调尺寸0.1.0-rc.8 (2026-08-20)
dsh-labnana2exoticknight/dsh-labnanaLabnana image generation for DeepSeek Harness: text-to-image / image-to-image / precise editing with credits estimation, subscription balance and web settings UI.0.1.0-rc.8 (2026-08-25)
dsh-model-capabilities-kalospac2Kalospacer/dsh-model-capabilitiesPer-model reasoning-effort and vision capability editor for DSH pi-ai provider profiles.0.1.1-rc.2 (2026-09-18)
dsh-paddle-ocr2omdsh-dev/dsh-paddle-ocrDSH PaddleOCR (百度 PaddleOCR-VL 文档布局解析) plugin: OCR tools plus a settings card and task panel0.1.0-rc.8 (2026-08-20)
dsh-paper-design2try-works/dsh-paper-design · npmPaper Design MCP bridge as a DeepSeek Harness bundle: paper_* tools, image screenshot support, design skills, OAuth auth, and Cursor-parity design guidance.0.1.0-rc.8 (2026-08-20)
dsh-paste-names2PaoMoXML/dsh-paste-namesPaste non-image files or folders into the DSH chat composer as native @path references (with plain-name fallback) instead of the images-only error.0.1.0-rc.8 (2026-08-21)
dsh-plugin-clawrouters2ropon/dsh-plugin-clawroutersOne-key ClawRouters plugin for DeepSeek Harness: chat, image generation, video generation, and web search0.1.0-rc.8 (2026-08-20)
dsh-plugin-custom-provider-enhancer2cinob/dsh-plugin-custom-provider-enhancerDeepSeek Harness plugin that enhances custom provider setup by auto-discovering models and auto-populating contextWindow, maxTokens, vision, and reasoning capabilities from models.dev0.1.0-rc.8 (2026-08-20)
dsh-pseudo-vision2DDDFXYqiming/dsh-pseudo-visionWraps the official DeepSeek adapter so every model is advertised as image-capable, then converts image blocks into OCR + color-statistics + pixel-scan + metadata text at request time — a fixed0.1.0-rc.8 (2026-08-20)
dsh-read-image2OoWJZZoO/dsh-read-imagePlug-and-play image reading for text-only models: admits pasted images, projects them as [Image #N], and provides a first-class read_image tool backed by a configurable vision model, with a 读图 sett...0.1.0-rc.8 (2026-08-20)
dsh-show-media2NecromanAlbert/dsh-show-mediaShow a local image or short video inside the current DeepSeek Harness conversation card, with click-to-preview. Does not replace the official read_image model path.0.1.1-rc.2 (2026-08-26)
dsh-sidebar-kaijia322kaijia323/dsh-sidebarVSCode-style file explorer for the DeepSeek Harness web client: a body-mounted, draggable right sidebar with virtualized lazy file tree and text / Markdown / image preview. Does not depend on the0.1.1-rc.2 (2026-08-26)
dsh-sight2Fu3rte/dsh-sight · npmPlug-in vision for text-only DeepSeek Harness models with built-in VLM presets and multi-image batch analysis.0.1.0-rc.8 (2026-08-20)
dsh-slide-reflex2lecutu/dsh-slide-reflexVision-free PPT engine bridge + live per-page preview panelunverified
dsh-think-ultra2YUEYUEXYS/dsh-think-ultraReasoning layer for the official DeepSeek Harness. Every outgoing request stays pinned to native max effort, with isolated Flash/Vision/Pro depth controls, stability axes, reasoning toolboxes and a0.1.1-rc.2 (2026-09-01)
dsh-tool-eyes2go-farther-and-farther/dsh-tool-eyesLocal vision 'eyes' for DeepSeek Harness (DSH): screen tool (capture screen or image -> local OpenAI-compatible VLM description) and ocr tool (Windows built-in OCR, zero model / GPU / cloud).0.1.0-rc.8 (2026-08-20)
dsh-tool-generate-image-zcldrago2zclDragon/dsh-tool-generate-image · npmModel-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.0.1.0-rc.8 (2026-08-20)
dsh-tui-browser-use2FlameTN7/dsh-tui-browser-useBrowser automation toolset for dsh-tui agents: Playwright-driven browser control with deepseek-v4-flash-vision-exp visual understanding.0.1.1-rc.2 (2026-09-01)
dsh-ui-customizer-finallx2Final-LX/dsh-ui-customizerFull DIY theme plugin for DSH web: color palettes, fonts, background image (upload/URL), glassmorphism, border radius.0.1.0-rc.8 (2026-08-20)
dsh-ui-spec2yumimanji/dsh-ui-spec · npmDeepSeek Harness plugin: turn UI screenshots into structured, implementation-grade web frontend specs. Deterministic geometry (sharp) + optional vision-model semantics, merged into one JSON +0.1.0-rc.8 (2026-08-20)
dsh-Veneer2swordordead/dsh-VeneerVeneer — a lightweight visual editor to reskin the DeepSeek Harness UI: edit background surfaces (color/image/opacity) with theme persistence.0.1.1-rc.2 (2026-09-01)
dsh-vision-314857492314857493/dsh-vision · npmDeepSeek Harness plugin: a deepseek-vision route that declares image input and transcribes pasted images via the free Zhipu GLM vision models before delegating to the DeepSeek adapter.0.1.0-rc.8 (2026-08-20)
dsh-vision-android2superclaude1/dsh-vision-androidVision + Android UI automation plugin for DeepSeek Harness: gpt-5.6-luna screenshot understanding and real-tap mobile app testing via adb0.1.0-rc.8 (2026-08-20)
dsh-vision-bridge-ximengxi2ximengxiaolan/dsh-vision-bridgeComposer-attached images are auto-described by an OpenAI-compatible vision model and handed to text-only models (DeepSeek) as text.0.1.0-rc.8 (2026-08-20)
dsh-vision-primitives2zouyuanqing/dsh-vision-primitivesNative interactive visual-reasoning plugin for DeepSeek Harness: precise pixel grounding (SOM grid, zoom, annotate, measure, diff, color, OCR) + MiMo V2.5 multimodal backend, with zero external MCP se0.1.0-rc.8 (2026-08-20)
dsh-vision-recognizer2kaixinbaba/dsh-vision-recognizer · npmDeepSeek Harness image recognition plugin: keep DeepSeek as the conversation brain while a configurable vision model (15+ providers, OpenAI-compatible + Anthropic) transcribes attached images.0.1.0-rc.8 (2026-08-20)
dsh-vision-reimucre2reimu-create/dsh-vision给纯文本模型自动配眼:图片消息自动桥接为视觉模型描述(日志内表面替换,不改写人类转录),附带 see_image 追问工具0.1.0-rc.8 (2026-08-20)
dsh-vision-router-nlqh72nlqh7/dsh-vision-routerCodex-style image offload for DeepSeek Harness: routes chat-box images to a user-configured vision model and feeds the text description back to a text-only primary model (e.g. deepseek-v4-pro).unverified
dsh-vision-shaking2shaking/dsh-vision为 DeepSeek Harness（dsh 插件）与 Claude Code（MCP）提供图片理解能力：本地 OCR（macOS Vision / Windows 内置 OCR）+ 云端 VLM（多供应商，OpenAI 兼容）0.1.0-rc.8 (2026-08-20)
dsh-vision-sjakdhasdh2sjakdhasdh/dsh-visiondsh-vision — a DeepSeek Harness plugin (tool template).0.1.0-rc.8 (2026-08-20)
dsh-vision-skill-dddfxyqi2DDDFXYqiming/dsh-vision-skillDSH standard vision skill: Qwen dynamic-resolution preprocessing + OpenAI-compatible VLM chain with failover/429 backoff, structured evidence mode, local tesseract-first long-screenshot OCR0.1.0-rc.8 (2026-08-20)
dsh-vision-wenjin2Wenjin-111/dsh-vision · npmDeepSeek Harness plugin: turn-level vision routing with provider fallback chains, a cached vision_describe tool with JSON output and image downscaling, and optional per-host proxy support.0.1.0-rc.8 (2026-08-20)
dsh-vision-window2shinegeer/dsh-vision-windowDSH 网页端识图插件（dsh-vision-window）：输入框旁可拖动的图片存储框，粘贴/拖入截图后自动存到工作区并把图片路径插到消息最前；自带 vision 工具 + 识图技能，让 AI 在长工程里自动调识图模型并整理到「已识别图片」文件夹。0.1.0-rc.8 (2026-08-20)
dsh-vision-xiaoshihou5142xiaoshihou514/dsh-visionLocal vision bridge for DeepSeek Harness0.1.0-rc.8 (2026-08-20)
dsh-vision-yepyeel2yepyeel/dsh-visionVision bridge for text-only models: describe attached images via another vision model or system OCR0.1.0-rc.8 (2026-08-20)
dsh-vqa-agent2jypjypjypjyp/dsh-vqa-agentvqa_ask 双模型视觉问答插件:主模型调用 vqa_ask 向视觉模型提问(图片字节真实送达),UI 实时展示"主模型提问 → 视觉模型回答"的 QA 过程,并在主设置提供多模态视觉模型选择页。0.1.0-rc.8 (2026-08-20)
dsh-xiapan-media2dongsheng123132/dsh-xiapan-mediaDeepSeek Harness native vision, gpt-image-2 image generation, and Seedance video generation via Xiapan Cloud.0.1.0-rc.8 (2026-08-20)
dsh-ymc-sidebar2kaijia323/dsh-ymc-sidebarVSCode-style file explorer for the DeepSeek Harness web client: virtualized, lazily loaded file tree in the right details column with text / Markdown / image preview.0.1.0-rc.8 (2026-08-20)
mcp-ds-ocr2BaihaWhite/mcp-ds-ocrOCR via OpenAI/Anthropic vision APIs for dsh: ocr_recognize tool (percent coords + two-diagonal-point boxes, auto region re-read on low confidence), a collapsible settings card in Settings → Plugins0.1.0-rc.8 (2026-08-20)
sidesight2ZhuXinAI/sidesight · npmVision sidecar for text-only coding agents.0.1.0-rc.8 (2026-08-20)
aitoearn-dsh-plugin1lussey820/aitoearn-dsh-pluginAiToEarn content-creation suite as a DeepSeek Harness plugin: creative director, script writer, image-text and video generation, and Douyin publishing.0.1.0-rc.8 (2026-08-20)
attach-plus1BaihaWhite/attach-plusDSH web-ui plugin: '/' glyph on the composer command-menu button plus a '+' attach button with separated image/document/other uploads.0.1.0-rc.8 (2026-08-20)
aura-vision1Ck-epsilon/aura-vision · npmAura Vision — free vision OCR plugin for DeepSeek Harness web profile: Zhipu GLM-4V-Flash (free tier), adaptive tile recognition for long documents, history with favorites and Markdown/Excel/Word/PNG0.1.0-rc.8 (2026-08-21)
chat-deepseek-vision1orrinzeng/chat-deepseek-visionDSH (DeepSeek Harness) 原生插件：通过 chat.deepseek.com 识图模式（model_type=vision）分析图片，免费、无需第三方视觉 API key。0.1.1-rc.2 (2026-09-04)
computer-use-vision1xuanyuanluoxue/computer-use-visionWindows computer-use capability for DeepSeek Harness: screenshot → vision model → simulated mouse/keyboard input, with self-evolving knowledge base.0.1.0-rc.8 (2026-08-25)
deepsee1chang416/deepsee · npmDeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery0.1.0-rc.8 (2026-08-20)
deepseek-harness-wecom-plus1fryghost/deepseek-harness-wecom-plusWeCom AI Bot channel bridge for DeepSeek Harness with template card support (text, image, file, Markdown + card pairing, button interactions, Web settings page)0.1.0-rc.8 (2026-08-20)
DeepSeek-harness-weixin1sliverp/DeepSeek-harness-weixinOfficial Weixin iLink QR-login text and image bridge for DeepSeek Harness0.1.0-rc.8 (2026-08-20)
dsh_omnivision1xiaozhengdeng/dsh_omnivisionOmniVision for DeepSeek Harness: an OmniParser-powered GUI agent plugin — screen capture, element recognition, click/type automation and a browser vision dock with recognition history, diffing and0.1.0-rc.8 (2026-08-20)
dsh_use_browser1ankye/dsh_use_browserCodex-style local browser automation: open / interact / screenshot / extract / eval via Playwright (headless or CDP to your Chrome)unverified
dsh-agnes1chaoliu615/dsh-agnesAgnes AI image & video generation tools for DSH (agnes_image_generate / agnes_video_generate)0.1.1-rc.2 (2026-08-26)
dsh-ai-image-design1satan9394/dsh-ai-image-designSQL 优化模式：EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents（38k MIT）启发。0.1.0-rc.8 (2026-08-20)
dsh-artifact-preview1nirvanaslash/dsh-artifact-preview · npmCodex-style artifact preview for DeepSeek Harness (DSH): produced-files row in chat with inline image thumbnails, and a resizable split-screen side preview panel rendering Markdown / source code /0.1.0-rc.8 (2026-08-20)
dsh-auto-vision1NormanFxxkingRockwell/dsh-auto-vision · npmDeepSeek Harness 视觉桥：自动发现你已配置的多模态模型，给纯文本主模型装上 vision 工具，识别结果以纯文本返回。零配置，一条命令安装。0.1.0-rc.8 (2026-08-20)
dsh-bing-search1Biogod2020/dsh-bing-searchNative DSH tool: batch VLM audit of image candidates with pure-text fallback.0.1.1-rc.2 (2026-09-04)
dsh-bridge-preview1xing666173/dsh-bridge-preview为 dsh-tool-vision 桥接导出的图片提供对话内联预览:用户粘贴的图片在气泡中显示缩略图,不改变桥接文本与模型行为0.1.0-rc.8 (2026-08-20)
dsh-browser-agent1Miiiuser/dsh-browser-agentCordis plugin that registers browser automation + vision tools (browser_*) for DeepSeek Harness, powered by the dsh-browser-agent CLI0.1.1-rc.2 (2026-09-04)
dsh-client-vision1ankye/dsh-client-visionModel-facing screen capture and external image-recognition tools with a pluggable channelunverified
dsh-composer-image-tools1ai-yucheng/dsh-composer-image-tools聊天输入框图片工具(自研):上传图片(≤10MB 防烧 token) + 自定义区域截图(Electron desktopCapturer),注入 DSH 草稿图片轨。零外部依赖。0.1.0-rc.8 (2026-08-24)
dsh-computer-use-renoned1Renoned/dsh-computer-useCapability-aware Computer Use for DeepSeek Harness: AX-first observation, measured native vision or Vision Router sidecar grounding, one hidden actuator, runtime lock, and verified actions.0.1.0-rc.8 (2026-08-25)
dsh-deepseek-vision-chengche1Cheng-cheng9669/dsh-deepseek-visionDeepSeek web vision bridge: give text-only DeepSeek models image recognition via a deepseek_vision tool0.1.0-rc.8 (2026-08-20)
dsh-deepseek-vision-router1mochgolf/dsh-deepseek-vision-routerTransparent image preprocessing route for DeepSeek Harness.0.1.0-rc.8 (2026-08-20)
DSH-Design-Studio1Sal7one/DSH-Design-StudioPersistent dual-face Design Studio plugin for the DSH harness: the design_studio agent tool (design systems under temp_design_folder/, identity presets, OpenRouter vision review, and a real0.1.0-rc.8 (2026-08-20)
dsh-diagram-design1satan9394/dsh-diagram-designSQL 优化模式：EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents（38k MIT）启发。0.1.0-rc.8 (2026-08-20)
dsh-drag-path1Rudyy898/dsh-drag-pathDrag non-image files/folders into DeepSeek Harness web and insert their real absolute paths into the composer — no more "only images allowed". 拖拽工程文件/文件夹进 DSH，自动定位真实绝对路径插入输入框。0.1.1-rc.2 (2026-08-28)
dsh-eye-vision1AlloyPlane/dsh-eye-visiondsh-eye-vision: give text-only DeepSeek Harness models eyes — image understanding via any OpenAI-compatible multimodal API. Fork of dsh-free-vision with custom-provider fixes and an0.1.0-rc.8 (2026-08-20)
dsh-eyes1Leeminjing/dsh-eyesOn-demand vision for text-only LLMs in DeepSeek Harness: keep pasted/attached images in the backend, and let the model call view_image to look at them anytime via any OpenAI-compatible vision0.1.0-rc.8 (2026-08-20)
dsh-generate-image1zemul/dsh-generate-imagedsh plugin: generate/edit images via the locally installed OpenAI Codex CLI0.1.0-rc.8 (2026-08-20)
dsh-grok-image1clarkzhao/dsh-grok-imageDeepSeek Harness plugin: Grok Imagine image generation as a model tool (subscription)0.1.1-rc.2 (2026-08-26)
dsh-grok-subscription1xisheng687/dsh-grok-subscriptionConnect an official Grok subscription to DSH as an ACP subagent, extending its native image support with audio and video tools.0.1.0-rc.8 (2026-08-20)
dsh-grok-vision1Sevncz/dsh-grok-visionHost-level grok_vision tool: local Grok CLI multimodal (image) analysis for every DSH session0.1.0-rc.8 (2026-08-20)
dsh-image-describe1sd1g1/dsh-image-describeDeepSeek Harness 宿主插件：让不支持图片输入的纯文本主模型也能"看图"（describe_image 工具 + 图片标记替换）0.1.0-rc.8 (2026-08-20)
dsh-image-gen-anywayon1Anyway-one/dsh-image-genImage generation plugin for DeepSeek Harness that calls gpt-image-2 through any OpenAI Images compatible endpoint, with in-conversation previews and a configurable settings card.0.1.1-rc.2 (2026-08-26)
dsh-image-mmx1fengs2021/dsh-image-mmx让文本模型（如 DeepSeek）在 DSH 里直接收发图片：图片落盘工作区、模型可见面自动替换为 mmx（MiniMax VLM）识别结果，用户侧照常显示缩略图。0.1.0-rc.8 (2026-08-20)
dsh-image-preview-ywleeo1ywleeo/dsh-image-preview在 dsh Web 对话正文中直接渲染本地图片与视频路径的插件（host 改写路径 + 客户端渲染播放器/拦截点击）0.1.0-rc.8 (2026-08-20)
dsh-image-search1zimai233/dsh-image-searchMulti-engine reverse image search aggregator for DeepSeek Harness. Turn one public image URL into Google Lens / Baidu / Yandex / TinEye / SauceNAO / IQDB / Ascii2d search links.0.1.0-rc.8 (2026-08-20)
dsh-image-tiler1meng-114/dsh-image-tilerDSH agent tool: slice a large image into labeled ~800x800 tiles plus an overview thumbnail, preserving detail for vision models.0.1.0-rc.8 (2026-08-24)
dsh-image-tools-junelear1JuneLearn/dsh-image-toolsMulti-provider image generation and editing tools for DeepSeek Harness0.1.0-rc.8 (2026-08-20)
dsh-image-unlock1FrostLeafKEE/dsh-image-unlockLift the 'model does not support images' gate in the DeepSeek Harness web GUI: declares image input for every llm-pi-ai model that does not state its own input modalities, so attachments are0.1.0-rc.8 (2026-08-20)
dsh-image-viewer1WSL043/dsh-image-viewerZoom, pan, download, gallery, and region-note image viewer for DeepSeek Harness0.1.1-rc.2 (2026-08-28)
dsh-image-vision1xsoc1/dsh-image-visionEyes for text-only DeepSeek: view_image tool (any OpenAI-compatible VLM, local Ollama or cloud) + chat image-attachment bridge that rewrites pasted/dropped images into view_image path markers0.1.0-rc.8 (2026-08-20)
dsh-image-vision-bridge1Icestab/dsh-image-vision-bridgeDSH 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.0.1.0-rc.8 (2026-08-20)
dsh-image-zoom1sijidoubi/dsh-image-zoomDeepSeek Harness plugin: click-to-zoom lightbox for markdown/chat images0.1.0-rc.8 (2026-08-20)
dsh-image-zoom-tianyitw1TianyiTwT/dsh-image-zoomSmart image splitting and zooming for vision models in the DeepSeek Harness: a labeled overview grid plus full-resolution region crops, returned inline as durable attachments.0.1.0-rc.8 (2026-08-24)
dsh-img1gmleong/dsh-img · npmGive text-only models eyes: an analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible vision endpoint. 给纯文本模型装上眼睛。0.1.0-rc.8 (2026-08-20)
dsh-imgdraw1NinjaSln-labs/dsh-imgdrawText-to-image for DeepSeek Harness: a draw_image model tool, an input-bar 生图 button with a prompt popup (async generation, 4-grid results, download / keep / delete), an /imgdraw image route, and0.1.1-rc.2 (2026-09-04)
dsh-imggen1Stellight/dsh-imggenDeepSeek Harness plugin: text-to-image output with in-chat image cards, download button, history gallery, and provider selection tabs0.1.0-rc.8 (2026-08-25)
dsh-inline-media-viewer-plugin1Wisdoverse/dsh-inline-media-viewer-pluginPersistent inline image, video, and audio previews for DeepSeek Harness Web conversations, with workspace-confined local reads and an optional ComfyUI proxy.0.1.1-rc.2 (2026-09-01)
dsh-llm-deepseek-vision1NagasakiSoyo-ui/dsh-llm-deepseek-visionVision-augmented DeepSeek adapter: a vision model describes images, then a text-only DeepSeek model reasons over the description.0.1.0-rc.8 (2026-08-20)
dsh-llm-image-bridge1caolong521/dsh-llm-image-bridgeImage-to-text bridge for text-only DeepSeek routes in DeepSeek Harness: OCRs image blocks into text before each generation call, so the DeepSeek chat-completions adapter can answer image promptsunverified
dsh-locallens1uknowmyface/locallensLocal macOS Vision OCR for DeepSeek Harness: read text from screenshots, clipboard images, or files with no upload.0.1.0-rc.8 (2026-08-20)
dsh-luna-vision-bridge1ycp424c/dsh-luna-vision-bridgeDSH LLM adapter that transcribes native image attachments with Codex Luna before delegating to DeepSeek0.1.0-rc.8 (2026-08-20)
dsh-maestro-diagram1ddtcorex/dsh-maestro-diagramMaestro diagram studio: mermaid_verify + mermaid_drift tools (hybrid with diagram-studio skill)0.1.1-rc.2 (2026-09-01)
dsh-media-tools1launchmaniac/dsh-media-toolsOpenRouter image, video, and speech generation as dsh tools, shipped as an out-of-tree profile bundle0.1.0-rc.8 (2026-08-25)
dsh-mimo-vision-hint1Isekai-Mfu/dsh-mimo-vision-hintDSH plugin: prompt the agent to dispatch image recognition to an opencode-go mimo-v2.5 subagent0.1.0-rc.8 (2026-08-20)
dsh-mindseye1kanchengw/dsh-mindseye · npmMindsEye: intent-routed vision, structured evidence, and exact cache for DeepSeek Harness0.1.0-rc.8 (2026-08-20)
dsh-mp-automator1VincentJiang06/dsh-mp-automatorWeChat Mini Program automated testing for DeepSeek Harness (dsh): selector-addressed actions, build-freshness gates, geometry-first assertions that work on text-only models, and screenshot image0.1.0-rc.8 (2026-08-20)
dsh-multi-tools1pirate-608/dsh-multi-toolsMultimodal tool suite for DeepSeek Harness: ModLens vision, local ComfyUI, Unity, creative apps, CAD, and Ren'Py.0.1.1-rc.2 (2026-09-01)
dsh-multimodal-lanbingy1lanbingyoumeng2023/dsh-multimodalOpenAI-compatible multimodal LLM adapter for DeepSeek Harness (image-capable).0.1.0-rc.8 (2026-08-20)
dsh-multimodal-sct192221SCT192221/dsh-multimodalMultimodal client plugin for DeepSeek Harness: inline image rows for generate_image/show_image tool cards, a turn-tail image gallery, and the multimodal settings page. Companion to the dsh-multimodal0.1.0-rc.8 (2026-08-21)
DSH-Multimodal-yauntyou1yauntyour/DSH-MultimodalDSH multimodal input plugin: route file attachments (images, video, audio, text) through per-preset model chains and feed the results to the session model as prompt tokens. Adds a Multimodal settings0.1.0-rc.8 (2026-08-20)
dsh-open-code-review1shengbinxu/dsh-open-code-reviewA DeepSeek Harness (dsh) plugin exposing alibaba/open-code-review (ocr) delegation mode as typed, model-facing tools.0.1.1-rc.2 (2026-09-04)
dsh-pdf-henryxia1henryxiao709/dsh-pdfA DeepSeek Harness (DSH) plugin that reads PDF files of any size (no 64KB limit): full Unicode text extraction (Chinese/English) via pdfjs-dist, with automatic OCR for scanned or image-heavy pages0.1.0-rc.8 (2026-08-20)
dsh-plugin-88api-image1blackdm666/dsh-plugin-88api-image88API Image Studio for DSH: four Image2 and Nano Banana models for text-to-image, multi-reference editing, 2K/4K output, and sequential batches.0.1.0-rc.8 (2026-08-25)
dsh-plugin-mm-vision1Elohia/dsh-plugin-mm-visionmm-vision (通感编码器) for DeepSeek Harness — give any text-only LLM the ability to see images via structured spatial text encoding. Registers the mm_vision tool.0.1.0-rc.8 (2026-08-20)
dsh-plugin-novelai1ysysz0343-web/dsh-plugin-novelaiNovelAI Diffusion V4.5 Full image generation for DeepSeek Harness: text-to-image, Danbooru tag lookup, and image-to-prompt reverse engineering.0.1.0-rc.8 (2026-08-20)
dsh-plugin-vision-tianbaid1Tianbaidi/dsh-plugin-visionAuxiliary vision for DeepSeek Harness: analyze images via an OpenAI-compatible vision endpoint (works with any main model)0.1.0-rc.8 (2026-08-20)
dsh-pro-vision1lasdrder0705/dsh-pro-visionLet DeepSeek-V4-Pro (text-only) use V4-Flash-Vision-Exp for attached images. Mac/Windows/Linux.0.1.0-rc.8 (2026-08-24)
dsh-pure-chat1niushuanan/dsh-pure-chatStart a chat immediately without a workspace, work mode, or execution permissions while keeping image and text-file uploads.0.1.1-rc.2 (2026-08-28)
dsh-qwen-mm-rrrosmon1RRRosmontis/dsh-qwen-mmQwen-MM-Plugins integration bundle for DeepSeek Harness: bundled multimodal skills, MCP server rows, and an image attachment bridge for text-only model routes0.1.0-rc.8 (2026-08-20)
dsh-qwen-vision1Asanagl/dsh-qwen-visionDeepSeek Harness plugin: Qwen-MM-Plugins vision (MCP) + paste-image-into-chat + image-vision skill0.1.0-rc.8 (2026-08-20)
dsh-rich-artifacts1Inkotake/dsh-rich-artifactsDeepSeek Harness Artifact/Deliverable plugin: publish workspace files as chat artifacts with inline image previews and download cards.0.1.0-rc.8 (2026-08-20)
dsh-screenshot1XEsx630/dsh-screenshotWeChat-style screenshot for the DeepSeek Harness composer: capture the screen (optionally hiding the DSH window), select a region, and attach the cropped image to the message as a file-card.0.1.0-rc.8 (2026-08-20)
dsh-screenshot-alainpro1Alain-Prot0s5/dsh-screenshotScreenshot-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。0.1.0-rc.8 (2026-08-24)
dsh-screenshot-capture1wangzhanchao883/dsh-screenshot-capturePoint-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 + evening0.1.0-rc.8 (2026-08-25)
dsh-screenshot-to-code1satan9394/dsh-screenshot-to-codeSQL 优化模式：EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents（38k MIT）启发。0.1.0-rc.8 (2026-08-20)
dsh-see-image1tiefeiyu/dsh-see-imagesee_image tool for DSH: route image files to any OpenAI-compatible vision model and relay the text description back to text-only models0.1.0-rc.8 (2026-08-20)
dsh-sight-ericfetc1ericfetch/dsh-sight · npmDeepSeek Harness plugin: direct multimodal image transfer declarations + per-session image clearing (surface replace), with a settings page and composer controls.0.1.0-rc.8 (2026-08-20)
dsh-ssh-files-sidebar1qigelunbiya/dsh-ssh-files-sidebarRemote SSH workspace and closed-loop deployment Agent for DeepSeek Harness: SSH Files, terminal, remote editing, zero-to-one Bootstrap, Runbooks, automation, Vision/OCR and safe recovery.0.1.1-rc.2 (2026-09-04)
dsh-sticky-notes-hufang361hufang360/dsh-sticky-notes便签 (sticky notes) client plugin for the dsh webui: floating, resizable post-it notes with markdown text and image notes, per-conversation binding, archived in browser localStorage.0.1.0-rc.8 (2026-08-20)
dsh-table-attach1yybukn/dsh-table-attachPaste or drag non-image files (xlsx/csv/pdf/zip…) into the DSH web composer: files are saved into the session workspace and an @reference is inserted.0.1.1-rc.2 (2026-09-01)
dsh-tool-agnes1Dingpenghui-good/dsh-tool-agnesDSH plugin for Agnes AI image generation (text-to-image)broken against 0.1.0-rc.6
dsh-tool-image-recognize1LuRia-yzk/dsh-tool-image-recognizeimage_recognize tool for DSH: recognize image content via a configurable vision model (OpenAI-compatible API), with auto/ocr/describe modes, magic-byte content validation, and sandbox-compliant file0.1.1-rc.2 (2026-09-04)
dsh-tool-imagegen1Github-CJX/dsh-tool-imagegenDSH 对话内联生图插件：OpenAI 兼容接口，图片以 generated-image 块直接显示在对话框内，设置项在 设置→插件→可配置。0.1.0-rc.8 (2026-08-20)
dsh-tool-vision-gloryxpn1gloryxpnv/dsh-tool-visionLocal-first vision for text-only DeepSeek Harness agents: route image understanding to a local OpenAI-compatible vision model, return structured JSON evidence (summary / OCR / layout / semantics /0.1.0-rc.8 (2026-08-20)
dsh-tool-vision-read1Mappedinfo/dsh-tool-vision-readDSH plugin: vision_read — route image reading to a dedicated vision model (e.g. Kimi K3) so text-only agents can see imagesunverified
dsh-turbo-agent1qianen6/dsh-turbo-agentSelectable DeepSeek Harness TurboAgent mode with hidden Best-of-N routing for Flash, Pro, and Vision.0.1.0-rc.8 (2026-08-25)
dsh-Unlimited-OCR-Skill1Aidenwu0209/dsh-Unlimited-OCR-SkillUnlimited-OCR long-document parsing with a native DeepSeek Harness tool and GUI configuration.0.1.0-rc.8 (2026-08-20)
dsh-upload-button1victorytianyi-dev/dsh-upload-buttonAdd an upload-image button beside the composer plus button. Picks local images and feeds them through the conversation draft-image drop path (DataTransfer + synthetic drop event), so describe-image0.1.0-rc.8 (2026-08-20)
dsh-v4flash-tiler1doublehappy123/dsh-v4flash-tilerDSH plugin: auto-tiles oversized chat images into labelled grid pieces (row/col metadata, overlap-aware, multi-image group isolation) so the DeepSeek vision model keeps fine detail instead of the0.1.1-rc.2 (2026-09-01)
dsh-vimina1Sunse666/dsh-viminaDeepSeek Harness Cordis plugin: drive Vimina Windows GUI automation via stdio (serve/call). Registers 26 vimina_* tools (scan/click/input/key/VMA scripts/screenshot/window/mouse).0.1.0-rc.8 (2026-08-20)
dsh-vision1kulebbb/dsh-vision · npmGive text-only DeepSeek models vision by describing images through an OpenAI-compatible vision model0.1.0-rc.8 (2026-08-20)
dsh-vision-analysis1Harvey-Will/dsh-vision-analysisModel-facing analyze_image tool for the DeepSeek Harness: multi-modal image understanding via any OpenAI- or Anthropic-compatible vision API, with 8 analysis modes, local path / http(s) URL / data0.1.0-rc.8 (2026-08-25)
dsh-vision-auto1babutiger/dsh-vision-autoDeepSeek Harness plugin: drag images into the Web GUI — images keep showing as images, image turns route to a vision model (route mode) or a built-in vision_describe tool answers them via any.0.1.0-rc.8 (2026-08-20)
dsh-vision-autoswitch1CultOfLuna/dsh-vision-autoswitchDeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.0.1.1-rc.2 (2026-09-04)
dsh-vision-bridge-goodandr1GooDAnDReaDY/dsh-vision-bridge · npmSelf-owned vision bridge for DeepSeek Harness: pick the vision model yourself from the available ones. Image content blocks are rewritten into text markers at the agent boundary so text-only models0.1.0-rc.8 (2026-08-20)
dsh-vision-bridge-lium1lium970320/dsh-vision-bridgeVision bridge for text-only main models: ingest chat images, turn them into text, and expose a view_image tool.0.1.0-rc.8 (2026-08-20)
dsh-vision-bridge-twistedr1TwistedRiCen/dsh-vision-bridge · npmDSH-native vision bridge for text-only models with native image attachments, multi-image evidence batching, and session-scoped validated Evidence caching.0.1.0-rc.8 (2026-08-20)
dsh-vision-bridge-xieweika1Xieweikang123/dsh-vision-bridgeGive a text-only dsh model eyes: pasted images are recognized into text via an OpenAI-compatible vision endpoint (Zhipu free by default) before the message reaches the model.unverified
dsh-vision-bridge-yulee3141YuLee-314/dsh-vision-bridge自包含的 DeepSeek Harness 视觉系统：DeepSeek 视觉孪生路由（原生图片体验 + 视觉桥请求层拦截）+ 本地 Ollama Agentic Vision 工具（describe/OCR/结构化扫描/区域查询/元素定位/双图对比/剪贴板）+ 粘贴分流（paste-to-path）。安装即用，无本机路径依赖。0.1.0-rc.8 (2026-08-20)
dsh-vision-edge-doubao1iceBear662/dsh-vision-edge-doubaoDSH 视觉插件（Edge 豆包桥接）：通用识图 + 数学建模图专项（几何图形/流程图/图表/表格/公式）+ 不确定项澄清闭环。零成本，免 API Key。0.1.0-rc.8 (2026-08-20)
dsh-vision-helper1Yuuz12/dsh-vision-helperPersistent vision plugin for DeepSeek Harness: registers the vision_analyze tool backed by a configurable multimodal model, with a settings-page UI. Zero dependencies.0.1.0-rc.8 (2026-08-20)
dsh-vision-kaaaaahn1kaaaaahn/dsh-visionDSH 本地视觉能力：macOS Vision OCR + ollama qwen3-vl 语义描述 + 上传图片桥接（图片块转文本，text-only 通道可用）0.1.0-rc.8 (2026-08-24)
dsh-vision-link1sprainJinyu/dsh-vision-link · npmLightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.0.1.0-rc.8 (2026-08-20)
dsh-vision-no-vision1wdwind/dsh-vision-no-visionGives a text-only LLM vision capability0.1.0-rc.8 (2026-08-20)
dsh-vision-plugin1Xin-Zhang-IceMan/dsh-vision-plugin · npmdsh-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 a0.1.0-rc.8 (2026-08-20)
dsh-vision-plugin-leifwang1Leif-Wang-021/dsh-vision-pluginVision capability for DeepSeek Harness: visionBridge auto-reads images via a multimodal model (deepseek stays the sole conversation model) + image_vision fallback tool + plugin-config card.unverified
dsh-vision-suite1princefrogdida-ux/dsh-vision-suiteWindows-first vision suite for DeepSeek Harness.0.1.0-rc.8 (2026-08-20)
dsh-vision-toggle1lijian-ui/dsh-vision-togglePer-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 Harness0.1.1-rc.2 (2026-09-01)
dsh-vision-tool1visail/dsh-vision-tool · npmImage routing for text-only models in DeepSeek Harness: a global analyze_image tool (Kimi vision) plus automatic rewriting of pasted images into attachment references when the active model cannot s...0.1.0-rc.8 (2026-08-20)
dsh-vision-yyking121yyking12/dsh-visionVision tool for DeepSeek Harness (dsh): the agent can understand images (local files, URLs, or conversation image attachments) through a user-configured OpenAI-compatible vision API, withunverified
dsh-web-file-upload1rrvvvnnn/dsh-web-file-upload · npmFile upload for the DeepSeek Harness web GUI: a folder button, paste, and drag-drop that save files into the session workspace uploads/, with file cards shown alongside image thumbnails.0.1.0-rc.8 (2026-08-20)
dsh-zhipu-vision1xingling80/dsh-zhipu-visionZhipu (智谱) GLM-4V vision understanding for DSH: agent tool zhipu_vision (local image path or URL + prompt) calls the Zhipu vision API and returns the model answer; paste-to-identify UX — pasting an0.1.0-rc.8 (2026-08-20)
easy-vision1Koreyer/easy-vision · npmA DeepSeek Harness tool plugin that lets a text-only agent 'see' local images: it reads an image file, auto-detects the real format, and returns (or writes to a Markdown file) a detailed textunverified
kepos-imagegen1LamplitIsles/kepos-imagegenKepos bridge image generation for DeepSeek Harness0.1.1-rc.2 (2026-09-01)
mimo-vision1wulusai2333/mimo-vision · npmDeepSeek Harness (DSH) native plugin: the describe_image tool, a vision bridge (image -> mimo-v2.5 -> text description) over the ctx.fs / ctx.credentials seams0.1.0-rc.8 (2026-08-20)
oh-my-dsh-llmpolsk1llmpolska/oh-my-dshOh My DSH — tiered model routing for DeepSeek Harness: think/build tiers, an automatic vision tier for images, and image generation through an ordinary chat model (e.g. gpt-5.6-luna on opencode-go)0.1.0-rc.8 (2026-08-20)
periscope1toRolex/periscopeperiscope 的 dsh（deepseek-harness）原生插件包 —— periscope-deepseek route 桥（声明 image 能力、纯文本委托 deepseek）+ describe 引擎副本；与主仓同构的零依赖 tsc && node --test0.1.0-rc.8 (2026-08-20)
prismrelay-mcp1Arnoldkevin/prismrelay-mcpVision-first MCP for text-only Agents, using Agnes AI for image understanding with experimental generation and editing.0.1.0-rc.8 (2026-08-20)
screenshot-review1wenyixiaoqingnian/screenshot-review截图审阅 dsh skill: 模型自己截图、自己看图、自己改代码，迭代优化前端效果0.1.1-rc.2 (2026-09-01)
slcatwujian-dsh-vision-plugin1yan5236/slcatwujian-dsh-vision-plugin让不支持图片输入的主模型通过已配置的视觉模型理解图片：自动把消息中的图片替换为带像素坐标系的文字描述，并提供 vision_ask 追问工具与设置页0.1.0-rc.8 (2026-08-20)
vision-translation1BingL-Li/vision-translation · npmNative dsh (DeepSeek Harness) Cordis plugin adapter for vision-translation: grounds images into via the Python CLI (PROTOCOL v1). Spawns cli.py, never re-implements core logic.0.1.0-rc.8 (2026-08-20)
c-vision0cczzyy-cn/c-visionVision DSH bundle: give the agent screen/window vision — see tool captures via the bundled Python cvision and returns the image natively0.1.0-rc.8 (2026-08-25)
cedardsh-model-probe0maiziman/cedardsh-model-probeAutomatic reasoning and image capability detection for custom DeepSeek Harness models0.1.1-rc.2 (2026-09-01)
deepseek-harness-extension0hypergraphdev/deepseek-harness-extensionDeepSeek Harness browser-extension edition: side panel with page-context awareness, vision-bridge multimodal image reading, and voice input0.1.0-rc.8 (2026-08-20)
deepseek-multimodel0CarlMarkswx/deepseek-multimodelUnified auxiliary-model plugin suite for DeepSeek Harness: vision + image generation behind one Auxiliary Models settings page, extensible to future modalities.0.1.1-rc.2 (2026-09-04)
dfy-dsh-plugins0xiaoxiao44443/dfy-dsh-pluginsShared image attachment references, validation and result projection for DFY DSH plugins.0.1.1-rc.2 (2026-09-01)
dsh-analyze-image-tool0CaseyTso/dsh-analyze-image-toolA vision bridge for text-only DeepSeek Harness models: registers an analyze_image tool that answers questions about images via ANY OpenAI-compatible vision/multimodal endpoint (SiliconFlow0.1.0-rc.8 (2026-08-20)
dsh-autovision0Junkrat9527/dsh-autovision · npmdsh auto-vision bridge: paste an image into a text-only model's composer and a configured multimodal model transcribes it as text, automatically.0.1.0-rc.8 (2026-08-20)
dsh-auxiliary0Gu-ZT/dsh-auxiliary · npmAuxiliary model routes for DeepSeek Harness: vision understanding and context compression through dedicated providers.0.1.0-rc.8 (2026-08-20)
dsh-baidu-ocr0pipiwolve/dsh-baidu-ocrBaidu cloud OCR (PaddleOCR-VL + Unlimited-OCR) for DeepSeek Harness Web: drag images/PDFs in, OCR to markdown, write results as local files.0.1.1-rc.2 (2026-08-26)
dsh-bcc0aixlb/dsh-bcc包拆拆 for DeepSeek Harness: video → script / storyboard / style guide. Uses the session model (recommend deepseek-v4-flash-vision-exp); never ships its own API keys.0.1.0-rc.8 (2026-08-24)
dsh-browser-ylwl19970ylwl1997/dsh-browserBrowser automation for DeepSeek Harness via bsk — navigate, snapshot, click, fill, and screenshot the user's real browser.0.1.0-rc.8 (2026-08-20)
dsh-bundle-vision0skillre/dsh-bundle-vision · npmVision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changes0.1.0-rc.8 (2026-08-20)
dsh-chat-image0Niobium-41-nb/dsh-chat-image · npmRenders chat Markdown image references (![alt](path title)) as a gallery under each closing assistant message0.1.0-rc.8 (2026-08-20)
dsh-client-paste-image0quei4r/dsh-client-paste-imagePaste clipboard images as file PATHS only on configured text-only routes: for listed models the paste is intercepted, saved through dsh-drop-caret's session upload route, and the path lands in the0.1.0-rc.8 (2026-08-20)
dsh-codex-canvas0mindcarver/dsh-codex-canvasDeepSeek Harness tool plugin: image generation (gpt-image-2) via the Codex CLI, with inline Web preview0.1.0-rc.8 (2026-08-20)
dsh-codex-image0xmasdong/dsh-codex-imageDeepSeek Harness plugin: Codex image generation/edit/vision tools backed by the local codex-image-bridge skill.0.1.0-rc.8 (2026-08-20)
dsh-codex-media0binsarjr/dsh-codex-mediaDocument and image analysis tools for agent harnesses, powered by a local OpenAI Codex CLI.0.1.0-rc.8 (2026-08-20)
dsh-computer-use-asdasdsd0asdasdsdsdasdasdasd/dsh-computer-useDeepSeek Harness plugin: Linux X11 computer-use tools (screenshot, mouse, keyboard) via a Python XTest helper0.1.1-rc.2 (2026-09-01)
dsh-computer-use-haifeiwu0haifeiWu/dsh-computer-useDSH plugin: local macOS computer use — screenshot/mouse/keyboard/browser control + OCR fallback for dsh (DeepSeek Harness)0.1.0-rc.8 (2026-08-20)
dsh-computer-use-macos0wangyong1972/dsh-computer-use-macosNative macOS Computer Use (screenshot + mouse/keyboard control) tool for DeepSeek Harness0.1.0-rc.8 (2026-08-25)
dsh-csv-and-image-preview0jetecho/dsh-csv-and-image-previewPreview images / SVG and CSV tables in the DeepSeek Harness chat, rendered as real browser / elements. Preview-first workflow: show the user the asset, wait for approval, then apply the
0.1.1-rc.2 (2026-09-01)
dsh-custom-logo0189-sketch/dsh-custom-logoReplace the DSH top-left BrandWordmark/FishLogo with your own image or text — an inline handle inside the wordmark, no floating widget0.1.0-rc.8 (2026-08-20)
dsh-deepseek-model-router0ZI-LV68/dsh-deepseek-model-routerAuto-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; includes0.1.0-rc.8 (2026-08-25)
dsh-deepseek-vision-bridge0KannaKuron/dsh-deepseek-vision-bridgeDSH plugin (DeepSeek vision bridge): give text-only agents vision through chat.deepseek.com's unofficial vision mode — WeChat-QR/password login in Settings, a deepseek_vision model tool, and0.1.0-rc.8 (2026-08-20)
dsh-deploy0mervyn-teo/dsh-deployDeployable Docker image for DeepSeek Harness (dsh web) with Caddy TLS + auth reverse proxy0.1.0-rc.8 (2026-08-25)
dsh-desktop-automation0Junkrat9527/dsh-desktop-automation · npmmacOS desktop control for DeepSeek Harness: agent operates non-browser apps (CapCut/PS/WPS/native clients) like a human — see screen, move mouse, type text. 14 tools + vision closed-loop0.1.0-rc.8 (2026-08-20)
dsh-desktop-hynahla0Hyna-hla/dsh-desktopDSH host plugin: OS-level desktop control tools (screen OCR with coordinates, mouse click/drag, Unicode typing, key combos) so the model can operate the whole browser including the address bar, and0.1.0-rc.8 (2026-08-20)
dsh-docker-devvikin0DevViking-Persike/dsh-dockerDeepSeek Harness plugin: Docker container, image, log, and Compose tools for the agent, over the local Docker CLI0.1.0-rc.8 (2026-08-25)
dsh-docs-protocti0protoctistmoses143/dsh-docsLocal PDF, Office, image, and OCR document intelligence for DeepSeek Harness.0.1.0-rc.8 (2026-08-20)
dsh-ds-vision-auto-route0litianshuo110/dsh-ds-vision-auto-routeRoute image-bearing turns to a configurable image-capable model for DeepSeek Harness0.1.0-rc.8 (2026-08-25)
dsh-eye0wenliang9527/dsh-eyeeye vision bridge — permanent dsh plugin: eye-vision virtual provider + llm/stream image intercept + eye_see tool + settings card (zero-dependency, inject-declared services)0.1.0-rc.8 (2026-08-20)
dsh-file-manager-toooooo60toooooo-6/dsh-file-managerDSH web file manager: workspace tree with semantic icons, preview (text / image / markdown / syntax highlight / large-file head), in-preview edit+save, create, delete, panel width drag and0.1.1-rc.2 (2026-09-02)
dsh-gemini-multimodal0RealAlexandreAI/dsh-gemini-multimodal · npmDeepSeek Harness plugin: multimodal tools (image/audio/video/document understanding, transcription, image generation) via Gemini API or the local Antigravity CLI.0.1.0-rc.8 (2026-08-20)
dsh-image0uckkk/dsh-image图片处理：读取图片尺寸/格式、缩放与格式转换（内置 ffmpeg，跨平台）0.1.0-rc.8 (2026-08-20)
dsh-image-amnesia0Choco-Zz/dsh-image-amnesiaKeep native vision, drop historical images before they hit relay providers. Global DeepSeek Harness bundle for every agent.0.1.1-rc.2 (2026-09-01)
dsh-image-conatiner0aa2246740/dsh-image-conatinerCodex-style generated-image gallery and lightbox for DeepSeek Harness0.1.0-rc.8 (2026-08-21)
dsh-image-dscriber0shuxu-zhao/dsh-image-dscriberGiving text models eyes to see in DeepSeek Harness.0.1.0-rc.8 (2026-08-20)
dsh-image-gallery0statem-li/dsh-image-gallery生图画廊：把会话里的 generate_image 工具结果渲染为并排缩略图画廊（点击放大、右键另存），不改动 DSH 源码0.1.0-rc.8 (2026-08-20)
dsh-image-gen-haimuhai0haimuhaimu/dsh-image-genDeepSeek Harness plugin: generate images via Aliyun Bailian Qwen-Image (bl CLI). Saves a conversation attachment, writes the file to ~/.dsh/image-gen/ and auto-opens it in the system viewer.0.1.0-rc.8 (2026-08-20)
dsh-image-generation0ankye/dsh-image-generationModel-facing image-generation tool with a settings-selected channel and normalized parametersunverified
dsh-image-generation-responses0Poepon/dsh-image-generation-responsesDeepSeek Harness Cordis plugin for Responses API image_generation: durable attachments and inline conversation rendering.0.1.0-rc.8 (2026-08-20)
dsh-image-model-router0Blue-2571/dsh-image-model-routerDeepSeek 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.0.1.1-rc.2 (2026-08-26)
dsh-image-picker0liujia-io/dsh-image-pickerDeepSeek Harness Web GUI 输入框 选图按钮:通过系统文件选择器添加参考图,绕开拖拽环境问题,复用官方附件管线(缩略图/上限校验/随消息上传)。Image-picker button for the conversation composer.0.1.1-rc.2 (2026-08-26)
dsh-image-preview0ReiRui/dsh-image-previewLocal image hosting for DeepSeek Harness: serves images from a preview directory over the web profile's own HTTP server so chat messages can render them inline, plus a preview_image tool that stages0.1.0-rc.8 (2026-08-20)
dsh-image-preview-eightfs0EIGHTfs/dsh-image-previewDSH 会话内图片预览服务：把工作区图片通过 HTTP 暴露给会话渲染、文本→图片渲染（双字体防乱码）、SVG→PNG 转换。AI 在回复里贴 markdown 图片 URL，用户直接在对话中看图。0.1.0-rc.8 (2026-08-20)
dsh-image-preview-leonardo0leonardoxr/dsh-image-previewInline previews and clipboard copying for DeepSeek Harness read_image tool calls, including nested Code Mode calls.0.1.0-rc.8 (2026-08-25)
dsh-image-read0Triple3h/dsh-image-readDeepSeek Harness plugin: structured image analysis via vision APIs (read_image_mimo tool) with Web UI config card. Attachment input moved to dsh-input-enhancement.0.1.0-rc.8 (2026-08-20)
dsh-image-resizer0HaijieChen/dsh-image-resizerResize oversized DSH Web conversation images before native attachment admission0.1.0-rc.8 (2026-08-25)
dsh-image-tiler-tiko95270Tiko9527/dsh-image-tilerDSH 高清图自动切片插件：发送前把大图切成 ≤800×800 小图，附带简洁设置页。0.1.0-rc.8 (2026-08-25)
dsh-image-to-text0HiSeax/dsh-image-to-text · npmDSH model tool that converts images to text (OCR + description) via configurable vision API providers, with image intake support for text-only models.0.1.0-rc.8 (2026-08-20)
dsh-image-uckkk0uckkk/dsh-image-uckkk图片处理：读取图片尺寸/格式、缩放与格式转换（内置 ffmpeg，跨平台）0.1.0-rc.8 (2026-08-20)
dsh-image-vision-veryint0VeryInt/dsh-image-visionSeamless image understanding for DeepSeek Harness: lets pure-text models read pasted/dropped images and Feishu/Lark images via a configurable vision model, without touching the host.0.1.0-rc.8 (2026-08-20)
dsh-imagedit0bbbz123/dsh-imageditLocal image editing toolkit for DeepSeek Harness: one image_edit tool for deterministic edits — cutout (quick flood-fill or rembg AI), trim, flip, rotate, brightness/contrast/saturation, blur0.1.0-rc.8 (2026-08-21)
dsh-imagegen-mario0360mario03690/dsh-imagegenImage generation + visual artifacts for DeepSeek Harness: text_to_image with a free trial, plus charts, diagrams, QR and badges — every artifact returns a URL ready to embed.0.1.0-rc.8 (2026-08-20)
dsh-imagegen-plugin0ShiXiangYu2/dsh-imagegen-pluginA DeepSeek Harness plugin that registers a generate_image tool (Qwen-Image / DeepSeek Janus-Pro-7B via SiliconFlow) callable by the model.0.1.0-rc.8 (2026-08-20)
dsh-imagegen-zhaojun20ZhaoJun233/dsh-imagegenProvider-neutral image generation tool for DeepSeek Harness0.1.0-rc.8 (2026-08-20)
dsh-imagen0CarlMarkswx/dsh-imagenImage generation capability seam for text-to-image modelsunverified
dsh-koboldcpp-hands0MicroHEROX/dsh-koboldcpp-hands · npmKoboldCpp for DeepSeek Harness - a tool plugin that lets the harness online model hand repetitive text and vision (OCR) labor to a local KoboldCpp (llama.cpp) server.0.1.0-rc.8 (2026-08-20)
dsh-latex-ocr0Yunnalab/dsh-latex-ocr公式图片 → LaTeX（pix2tex / LaTeX-OCR）：把教材/截图中的数学公式识别为 LaTeX 代码0.1.0-rc.8 (2026-08-20)
dsh-llm-codex-auth-native-compact-image0thaning0/dsh-llm-codex-auth-native-compact-imageCodex OAuth provider with native compaction and image input support for DeepSeek Harness.0.1.0-rc.8 (2026-08-20)
dsh-llm-mlx0robbywang25/dsh-llm-mlxDeepSeek Harness plugin for local MLX-LM and MLX-VLM models with loopback-only defaults and optional managed server startup0.1.1-rc.2 (2026-08-26)
dsh-llm-vision01710782766/dsh-llm-vision · npmModel-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, with0.1.0-rc.8 (2026-08-20)
dsh-llm-vision-router0dmsobtl/dsh-llm-vision-routerDSH plugin: auto-route to a multimodal model when messages contain images, stay on the cheap model otherwise.0.1.1-rc.2 (2026-09-04)
dsh-local-ocr0littlewrite/dsh-local-ocrA local OCR library and DeepSeek Harness plugin for macOS and Windows.0.1.0-rc.8 (2026-08-20)
dsh-mac-vision0Kevoyuan/dsh-mac-vision · npmNative macOS OCR and Vision tools for DeepSeek Harness0.1.0-rc.8 (2026-08-20)
dsh-maclens0Harzva/dsh-maclensBridge Apple's on-device Vision framework (macOS) into DeepSeek Harness: OCR, image classification, face detection, and document layout as local dsh tools. No network, no API key, no daemon.0.1.0-rc.8 (2026-08-20)
dsh-macos-vision-ocr0leozou320-ai/dsh-macos-vision-ocrOffline macOS Vision OCR tool for DeepSeek Harness0.1.0-rc.8 (2026-08-20)
dsh-math-input0xiaxi626/dsh-math-inputZero-token offline math input for DeepSeek Harness: handwriting recognition, screenshot OCR, LaTeX editor, and inline LaTeX rendering.0.1.1-rc.2 (2026-09-02)
dsh-memes0kagura-agent/dsh-memesDSH plugin: meme/reaction picker for DeepSeek Harness agents. No memes, no soul. Picks the right reaction image from the kagura-agent/memes library at runtime — semantic tag matching over 260.1.0-rc.8 (2026-08-20)
dsh-mermaid-smooth0gitByteFree/dsh-mermaid-smoothRender mermaid fences in dsh web chat as diagrams by default with smooth zoom/pan, per-fence diagram/code toggle at top-right, persisted per-fence preference, dark-mode follow, and full offline0.1.1-rc.2 (2026-09-01)
dsh-mermaid-zoom0evanfang0054/dsh-mermaid-zoom · npmMermaid diagram enhancement for the DeepSeek Harness (DSH) web GUI: Ctrl/Cmd+wheel zoom, drag to pan, double-click reset, hover toolbar with zoom controls and 2x PNG copy. Pure client-side DOM0.1.0-rc.8 (2026-08-20)
dsh-minimax-image0Jack-sun-learner/dsh-minimax-imageMiniMax 文生图插件：把一句话画面描述生成图片并保存到工作区，作为 image-gen 工具提供给模型调用。0.1.0-rc.8 (2026-08-20)
dsh-mmx0crazyma99/dsh-mmxMiniMax CLI bridge for DeepSeek Harness (dsh): mmx-backed web search fallback and transparent image understanding, with first-run onboarding and a settings card.0.1.0-rc.8 (2026-08-25)
dsh-model-auto-hot-switch0SHUJILAI/dsh-model-auto-hot-switchAutomatic per-task model hot-switching for DeepSeek Harness (dsh): image-aware tasks route to the vision model automatically, every other task keeps your default model. Zero extra tokens, no context0.1.1-rc.2 (2026-09-01)
dsh-model-capabilities-lylarche0lylarcher/dsh-model-capabilitiesDSH Settings section to edit per-model input modalities (text/image) AND reasoningEfforts (incl. custom wire values), for all configured providers, models and modelOverrides at once — a companion to0.1.1-rc.2 (2026-09-01)
dsh-model-caps0raomaiping-hash/dsh-model-capsModel capability editor for DeepSeek Harness Web: per-model reasoning-effort levels (thinking intensity) and input modalities (multimodal) for custom llm-pi-ai providers — fields the official Models0.1.1-rc.2 (2026-09-01)
dsh-model-manager0hrhgit/dsh-model-managerModel tags, reasoning capabilities, image routing, and vision proxy support for DeepSeek Harness0.1.1-rc.2 (2026-09-01)
dsh-model-vision-capability0dwkejiPeng/dsh-model-vision-capability为 llm-pi-ai 中的模型单独声明原生图片输入能力，并配置可用的思考强度与默认思考等级。0.1.1-rc.2 (2026-08-26)
dsh-multimedia-viewer0chaiyujin/dsh-multimedia-viewerBrowse images and video from the current workspace inside the harness page: floating button, filtered thumbnail grid, lightbox and inline playback. Scoped to the session cwd.unverified
dsh-multimodal-runtime0mogudesu/dsh-multimodal-runtimeMogu Multimodal Runtime - DeepSeek Harness 统一多模态能力运行时 (Comfy Local Provider V1)0.1.1-rc.2 (2026-09-01)
dsh-ocr0haifeiWu/dsh-ocrDSH plugin: local OCR and image understanding for dsh — inlined image previews in Web tool cards0.1.0-rc.8 (2026-08-20)
dsh-ocr-bridge0vuvanmai936-dot/dsh-ocr-bridge · npmPaste images into DeepSeek Harness chat and have them read by a free local backend (macOS Vision / Tesseract) before the text-only DeepSeek model answers0.1.0-rc.8 (2026-08-20)
dsh-ocr-plugin-xbyskill0xby-skill/dsh-ocr-pluginDeepSeek Harness OCR 插件 — 基于小笨羊 OCR 能力，为纯文本模型提供图片文字识别功能0.1.1-rc.2 (2026-08-28)
dsh-ocr-review0jiayan-xu/dsh-ocr-reviewLocal OpenCodeReview (ocr) gate for dsh: ocr_review tool runs AI code review on a workspace/branch diff via the managed node install, returns structured findings and optional gate failure.0.1.0-rc.8 (2026-08-20)
dsh-omni-vision0Renji004/dsh-omni-visionA canvas the agent draws on and then sees: eyes_render draws text/shapes in the Web GUI, stores the PNG locally, and hands the result back to the model. Windows-only: eyes_ocr reads text via the0.1.0-rc.8 (2026-08-20)
dsh-onebot-mario8410mario841859784/dsh-onebotQQ bot channel for dsh via the OneBot 11 protocol (NapCat / Lagrange / LLOneBot / go-cqhttp): reverse- or forward-WebSocket, DM + group chats with mention gating and allowlists, inbound image/voice0.1.1-rc.2 (2026-09-04)
dsh-paddle-ocr-tenglong0tenglongbohai/dsh-paddle-ocrDSH DeepSeek Harness plugin: Add PaddleOCR vision to text-only LLMs (Agnes, DeepSeek, MiniMax, GLM, Mimo). 为DeepSeek Harness纯文本模型添加图片识别能力，支持本地截图和文档OCR。0.1.0-rc.8 (2026-08-20)
dsh-pdf-reader-ydlstart0ydlstartx/dsh-pdf-readerAI-powered PDF reader for DeepSeek Harness with annotations, multi-PDF workflows, mixed image-text evidence, and on-demand OCR.0.1.0-rc.8 (2026-08-25)
dsh-pdf-to-word0dy395769511-star/dsh-pdf-to-wordDeepSeek Harness plugin: PDF→Word (.docx) conversion with layout fidelity (fonts/tables/images/borders), OCR scan mode, and optional multimodal LLM verification. Registers the pdf_to_word model tool.0.1.1-rc.2 (2026-09-01)
dsh-periscope0lmh-2026/dsh-periscopeDSH plugin: keep text-only models (deepseek-v4-flash / deepseek-v4-pro) as the session default, and automatically route requests that carry image content to a configured vision-capable model0.1.0-rc.8 (2026-08-25)
dsh-pilot-viger10Viger1/dsh-pilot · npmHands for your DeepSeek Harness agent — autonomous browser operation with a native permission model. Accessibility-ref page snapshots let a text-only model navigate, act, and test without vision or0.1.0-rc.8 (2026-08-20)
dsh-plan-router0unable-splanck/dsh-plan-routerDeepSeek Harness plugin: plan with an expensive vision model, compress context with a cheap reader model, verify with an independent reviewer model, and code with the session model0.1.1-rc.2 (2026-09-04)
dsh-playwright-whklwhkl0whklwhkl/dsh-playwrightPlaywright browser automation tools for DSH: open pages, click, type, fill, extract, screenshot.0.1.1-rc.2 (2026-09-04)
dsh-plugin-android-use0HuanLinOTO/dsh-plugin-android-useDSH plugin exposing adb-based tools that let the model operate an Android phone (screenshot, UI dump, tap, swipe, input text, press keys, open apps). | 让模型通过 adb 操作安卓手机的 DSH 插件（截图、UI0.1.1-rc.2 (2026-09-04)
dsh-plugin-docstudio0Sudo-Biao/dsh-plugin-docstudioDocumentStudio tools for DeepSeek Harness — bidirectional document conversion (X↔Markdown), templates, PDF merge, and image extraction as model-facing tools.unverified
dsh-plugin-glm-vision0baldovinmarques391-design/dsh-plugin-glm-visionImage translation for non-multimodal models via GLM-4V-Flash: intercepts images, generates descriptions, injects as text.0.1.0-rc.8 (2026-08-21)
dsh-plugin-grok0toolazytoname/dsh-plugin-grokDeepSeek Harness plugin: drive the local Grok Build CLI for text, image, and video.0.1.0-rc.8 (2026-08-20)
dsh-plugin-image-gen0tuofangzhe/dsh-plugin-image-genOpenAI-compatible image generation tool for DeepSeek Harness0.1.1-rc.2 (2026-08-28)
dsh-plugin-image-tools0Pasumao/dsh-plugin-image-tools · npmDSH 图片插件：ask_user_choice 图片/图文混合选项（Web GUI 渲染图片选择卡，可放大查看）+ show_images 在回复中内嵌图片（图片与文字混排）。图片来源支持本地路径 / http(s) URL / base64 data URI。纯插件实现，不改核心包。0.1.0-rc.8 (2026-08-20)
dsh-plugin-inline-image0usavv1547-cyber/dsh-plugin-inline-imageDSH web plugin: serve workspace image files over a constrained /dsh-image route so agents can embed images inline in conversation.0.1.0-rc.8 (2026-08-20)
dsh-plugin-kie-ai0MarceloSenai/dsh-plugin-kie-aiDeepSeek Harness plugin: image and video generation over the KIE AI API, with polling to completion and a status query0.1.1-rc.2 (2026-09-04)
dsh-plugin-local-vision0linktao159357/dsh-plugin-local-visionDeepSeek Harness 本地视觉插件：通过 LM Studio 本地视觉模型描述图片/截图，全本地、无云端依赖。提供 vision_describe 工具（Node 原生后端，可选 Python 压缩后端）。0.1.1-rc.2 (2026-09-04)
dsh-plugin-multimodal-bridge0avaritiachaos/dsh-plugin-multimodal-bridge · npmDynamic multimodal-to-text projection and cross-model vision bridge for DeepSeek Harness (dsh), allowing seamless hot-switching between vision models (Gemini/Claude) and text-only models (DeepSeek).0.1.0-rc.8 (2026-08-21)
dsh-plugin-qiuchunh0qiuchunhuimax/dsh-pluginWorkspace-confined PaddleOCR tool and /ocr command for DeepSeek Harness.0.1.0-rc.8 (2026-08-20)
dsh-plugin-show-image0justhalfbit/dsh-plugin-show-imageRender local image files inline in the DSH conversation via a global show_image tool.0.1.1-rc.2 (2026-09-02)
dsh-plugin-vision0MoneShadow/dsh-plugin-visionVision assist for DeepSeek Harness: lets the main model see images through an OpenAI-compatible vision API0.1.0-rc.8 (2026-08-20)
dsh-plugin-vision-bridge0lcb522/dsh-plugin-vision-bridgeVision bridge: read_image is transparently served by a configurable vision model (default zai/glm-4.6v) when the session model is text-only; the description returns as text and the session keeps its0.1.0-rc.8 (2026-08-20)
dsh-plugin-vision-coelly0co-Elly/dsh-plugin-visionVision capability plugin for DeepSeek Harness — enables pure-text LLMs to analyze images via GLM-4V-Flash0.1.1-rc.2 (2026-09-04)
dsh-plugin-vision-qizhen200qizhen2021/dsh-plugin-visionThe see tool for the DeepSeek Harness: offline OCR with positions (macOS Vision) + ASCII layout art (PIL) + vision-model semantic description (mimo-v2.5 via the opencode-go gateway). Works with any0.1.0-rc.8 (2026-08-20)
dsh-plugin-vision-toolkit0YYTbit/dsh-plugin-vision-toolkit · npmVision toolkit for DeepSeek Harness -- glance, ground, detect, crop CLI tools for text-only agents to understand images0.1.0-rc.8 (2026-08-20)
dsh-plugin-zai-mcp0nekomona/dsh-plugin-zai-mcpBridges the four z.ai GLM Coding Plan MCP servers into DeepSeek Harness via the in-box @deepseek-ai/dsh-mcp-client: vision (GLM-4.6V stdio via npx @z_ai/mcp-server), web reader, web search prime, and0.1.0-rc.8 (2026-08-20)
dsh-plugin-zhishe-baojia-shenhe0siweimofang/dsh-plugin-zhishe-baojia-shenhe知设装修报价审核插件 - 装修报价单智能审核与风险识别(异常单价识别+漏项检测+地区价格对标+视觉OCR截图输入)0.1.0-rc.8 (2026-08-25)
dsh-plugins-aetheria0Aetheri-AI/dsh-pluginsDeepSeek Harness plugin: a model-facing show_image tool that presents a local image to the human viewer in the conversation.0.1.1-rc.2 (2026-09-01)
dsh-plugins-ganymede0GanymedeNil/dsh-pluginsInline mermaid 11.17.0 diagram rendering for the dsh web chat, following the light/dark theme, with SVG/PNG download0.1.0-rc.8 (2026-08-25)
dsh-plugins-neoeto0neoeto/dsh-pluginsInline D2 diagram display for the d2_render tool: renders the generated SVG inside the conversation tool card0.1.0-rc.8 (2026-08-20)
dsh-postman0zhousun55-byte/dsh-postmanDeepSeek Harness web plugin — upload files and folders straight into the conversation (no workspace copy needed): images attach as real image blocks, text content is written into the composer0.1.0-rc.8 (2026-08-20)
dsh-preview0Viger1/dsh-preview · npmEyes for your DeepSeek Harness agent — it opens, sees, and fixes what it builds. Headless-browser preview & self-verification tools (screenshot, console, DOM read, interact) as a dsh plugin.0.1.0-rc.8 (2026-08-20)
dsh-pro-vision-std0lasdrder0705/dsh-pro-vision-stddsh-std Community v0.15 ModelProvider: DeepSeek-V4-Pro with images captioned by V4-Flash-Vision-Exp. Requires @dsh-std/adapter-dsh on DeepSeek Harness.0.1.1-rc.2 (2026-08-26)
dsh-provider-pro0Mortal520/dsh-provider-proCustom provider enhancements: User-Agent override, reasoning-level switching, and image-input declaration for DSH custom providers · 自定义供应方增强：UA 覆盖、推理等级切换、图片输入声明。0.1.1-rc.2 (2026-09-04)
dsh-quicksight0Isanti2016/dsh-quicksight · npmTwo-tier image reading for text-only models in DeepSeek Harness: fast local OCR (RapidOCR, offline) first, then a vision model via modlens as fallback.0.1.0-rc.8 (2026-08-20)
dsh-qwen-multimodal0wuwangmao/dsh-qwen-multimodalDSH bundle: Qwen multimodal bridge — vision (qwen3-vl), speech-to-text (qwen3-asr), text-to-image (qwen-image), via the deepseek-vision skill scripts0.1.0-rc.8 (2026-08-20)
dsh-rapid-ocr-ui0kid-tea/dsh-rapid-ocr-uiDual-face (host + client) plugin: independent text-output ocr_image tool + tools/execute read_image capability dispatch + ctx.ocr seam, with a conversation.input.left OCR toggle button.0.1.0-rc.8 (2026-08-20)
dsh-read-image-plugin0dddzzz123-dz/dsh-read-image-pluginImage input fallback for DeepSeek Harness with native multimodal model detection and Volcengine Ark vision.0.1.0-rc.8 (2026-08-25)
dsh-schematic0Mason-1011/dsh-schematicLive plugin-topology viewer for DeepSeek Harness: the wiring diagram of every mounted plugin, its runtime activity, a composer-side star map — and a composition workbench that edits the wiring on the0.1.1-rc.2 (2026-09-01)
dsh-screen-agent0lak321/dsh-screen-agentDesktop & web UI automation for DSH: full-screen capture, Windows OCR, mouse click/drag, typing, key press, window activate, plus battle-tested Paint drawing capability0.1.0-rc.8 (2026-08-20)
dsh-screenshot-diff0PangYiMing/dsh-screenshot-diffPixel-diff two screenshots into diff.png + a labeled triptych (pixelmatch)0.1.0-rc.8 (2026-08-20)
dsh-screenshot-paste0PdxGame/dsh-screenshot-pasteScreenshot/file paste board for the DSH Web GUI: paste, drag or browse to save files locally, show reference chips above the input, and auto-append file paths when sending a message.0.1.0-rc.8 (2026-08-20)
dsh-screenshot-plugin0deepseekbluefish/dsh-screenshot-pluginWeChat-style in-app screenshot button for DeepSeek Harness: drag to capture a screen region, PNG saved with auto-numbering, marker [Shot N HH:mm] written into the composer.0.1.0-rc.8 (2026-08-25)
dsh-shots0dat-lequoc/dsh-shotsShots tab for DeepSeek Harness: a video-player view (live + YouTube-style scrubber) over a browser daemon's screenshot feed in /shots/0.1.0-rc.8 (2026-08-25)
dsh-show-image-kurekaru0KureKaruna/dsh-show-imageWeb UI plugin: send workspace images to the user as chat attachments (show_image tool + chat gallery node)0.1.0-rc.8 (2026-08-25)
dsh-siliconflow-vision0ShiXiangYu2/dsh-siliconflow-vision · npmDSH 插件：通过硅基流动(SiliconFlow)视觉大模型识别/分析图片，支持本地文件路径、http(s) 图片 URL 与 base64 data URL。0.1.0-rc.8 (2026-08-20)
dsh-simpletex-ocr0Huoer9527/dsh-simpletex-ocr · npmSimpleTex 专用 OCR/公式识别工具 simpletex_recognize：task=formula 返回 LaTeX（含置信度），task=text 返回 Markdown，task=auto 按问题关键词路由。GUI 设置卡热配置 token/端点/上限。0.1.0-rc.8 (2026-08-21)
dsh-sprite-gen0randomix777/dsh-sprite-genSprite Sheet Generator with AI Image Generation0.1.1-rc.2 (2026-09-01)
dsh-subagent-vision0niuniuaba/dsh-subagent-vision · npmdsh 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.0.1.0-rc.8 (2026-08-20)
dsh-telegram-gum970Gum97/dsh-telegram · npmTelegram channel for DeepSeek Harness — rich tables and lists, real image delivery both ways, inline-keyboard questions, and in-chat model/preset/mode control0.1.0-rc.8 (2026-08-21)
dsh-text2img-compress0Nigel211/dsh-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 Harness0.1.0-rc.8 (2026-08-25)
dsh-tool-accurate-vision0imkingjh999/dsh-tool-accurate-vision · npmModel-facing accurate_vision tool: precise image spatial reasoning via a vision model0.1.0-rc.8 (2026-08-20)
dsh-tool-pdf-huanyuta0HuanyuTan777/dsh-tool-pdfModel-facing PDF tools for DeepSeek Harness: read metadata, extract text, and render pages for vision/OCR0.1.1-rc.2 (2026-09-04)
dsh-tool-vision-pzqian120pzqian123/dsh-tool-vision · npmDSH plugin: read images through a user-configured vision-capable model when the main model route cannot accept image input0.1.0-rc.8 (2026-08-20)
dsh-toolbelt0cking000bigdemon/dsh-toolbeltEight DeepSeek Harness plugins: persona, language guard, vision fallback, python workdir guard, windows encoding guard, cross-agent memory, image generation, and skill shell injection.0.1.0-rc.8 (2026-08-20)
dsh-ui-external-vision0xiyue718/dsh-ui-external-visionExternal vision model plugin for image recognition when the active model lacks vision0.1.0-rc.8 (2026-08-20)
dsh-umi-ocr-vision0paul-yangmy/dsh-umi-ocr-visionUmi-OCR vision bridge for DeepSeek Harness: when the main model is text-only, OCR images with local Umi-OCR and let the original DeepSeek model answer.0.1.0-rc.8 (2026-08-20)
dsh-unsloth-hands0MicroHEROX/dsh-unsloth-hands · npmUnsloth for DeepSeek Harness - a pure-client tool plugin that connects the harness online model to a locally running Unsloth Desktop (Unsloth Studio) server for repetitive text and vision (OCR) labor.0.1.0-rc.8 (2026-08-20)
dsh-vidgen-plugin0xsluck/dsh-vidgen-pluginMulti-provider AI video/image generation plugin for DeepSeek Harness (DSH). ComfyUI-style node canvas studio + multi-provider settings, with agent tools list_video_models / generate_video /0.1.0-rc.8 (2026-08-20)
dsh-vision-anyiqaq0Anyi-qaq/dsh-visionBrowser settings UI for the dsh-vision plugin: a Vision section on the Settings page and a configuration card in the Plugins → Plugin configuration tab.0.1.0-rc.8 (2026-08-20)
dsh-vision-assist0wjling/dsh-vision-assistDeepSeek Harness 视觉助手插件：给没有视觉能力的模型配一个可随时切换的多模态识别模型。输入框图片自动落盘并改写为文本提示，主模型调用 vision_recognize 工具即可完成看图；识别模型在 settings 的 vision-assist 命名空间热更新切换。0.1.1-rc.2 (2026-09-04)
dsh-vision-bridge-abdullah0AbdullahElTiby/dsh-vision-bridge · npmVision bridge for text-only models (DeepSeek and any route without image input): Gemini Flash describes attached images at the llm/stream seam and provides the describe_image tool.0.1.0-rc.8 (2026-08-20)
dsh-vision-bridge-c4c40C-4-C-4/dsh-vision-bridgeVision Bridge — a persistent DeepSeek Harness plugin that gives the text-only DeepSeek model image understanding by bridging to user-configured vision model APIs (OpenAI-compatible / Google Gemini).0.1.0-rc.8 (2026-08-20)
dsh-vision-bridge-shiragaw0ShiraGawaAnri/dsh-vision-bridgeDSH profile bundle: auto-bridge images for text-only models (DeepSeek etc.) — instead of the native "model does not support images" rejection, the image is materialized into the workspace and the0.1.0-rc.8 (2026-08-20)
dsh-vision-bridge-skill0LittleInk/dsh-vision-bridge-skillDeepSeek adapter wrapper for the dsh web profile: describes image attachments via an OpenAI-compatible vision API (DashScope qwen-vl-max by default), then delegates the text-only request to DeepSeek.0.1.0-rc.8 (2026-08-20)
dsh-vision-bridge-yinxe0Yinxe/dsh-vision-bridgeDeepSeek Harness (DSH) vision bridge: let text-only models delegate image understanding to multimodal vision models via vision_describe tool, with persistent settings UI and primary/fallback0.1.1-rc.2 (2026-09-04)
dsh-vision-bridge-zhuhb0Zh-U-hB/dsh-vision-bridgeDeepSeek Harness plugin: bridge image-bearing messages to a user-configured OpenAI-compatible vision endpoint when the active text model cannot see images0.1.0-rc.8 (2026-08-20)
dsh-vision-bridge-zzdream60zzdream67/dsh-vision-bridgeLet text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.0.1.0-rc.8 (2026-08-25)
dsh-vision-check0uckkk/dsh-vision-checkvisioncheck：视力屈光度：按参数精确计算，返回明确建议（医疗内容请遵医嘱）。0.1.0-rc.8 (2026-08-21)
dsh-vision-damie0Da-Mie/dsh-visionDSH vision subagent plugin: delegates image recognition to the DeepSeek vision model0.1.0-rc.8 (2026-08-25)
dsh-vision-guard0good-boy4069/dsh-vision-guard · npmTransparent image guard + vision analysis for DeepSeek Harness: text-only models read pasted images without the 400 session deadlock.0.1.0-rc.8 (2026-08-20)
dsh-vision-harryli70HarryLi-7/dsh-visionDSH vision plugin: image recognition (Codex + Zhipu fallback) and generation (GPT Image + CogView fallback), text-only-model safe0.1.0-rc.8 (2026-08-20)
dsh-vision-helper-statemli0statem-li/dsh-vision-helper辅助视觉模型：图片→文本描述，供文本模型、浏览器截图兜底与聊天贴图降级使用0.1.0-rc.8 (2026-08-20)
dsh-vision-lakeofsk0lakeofsky347/dsh-visionVision Bridge plugin for the DeepSeek Harness: routes attached images to a vision-capable model (default xiaomi/mimo-v2-omni) and feeds the text description back to text-only routed models such as0.1.0-rc.8 (2026-08-20)
dsh-vision-ocr0wangxiang0605qvq/dsh-vision-ocrDSH 图片识别插件：输入框一键选图发送识别请求（需自备支持图像输入的模型与 API Key）unverified
dsh-vision-patch0ryasrk/dsh-vision-patchPer-model and per-route image-input (vision) checkboxes on the Models page's custom-provider cards, writing through the llm-pi-ai settings namespace.0.1.1-rc.2 (2026-09-04)
dsh-vision-plugin-zcma110zcma11/dsh-vision-pluginDeepSeek Harness plugin: upload/paste images in the chat box; on send, transcribe via a vision model (dashscope) or offline Windows OCR, then inject the description into the message as 【解析了提供图片0.1.0-rc.8 (2026-08-20)
dsh-vision-pro-bridge0ShaineDemo/dsh-vision-pro-bridgeGive text-only DeepSeek-V4-Pro real vision with zero new dependencies and DeepSeek-only routing: images are described by deepseek-v4-flash-vision-exp (your existing DEEPSEEK_API_KEY), then the text0.1.1-rc.2 (2026-09-04)
dsh-vision-proxy-nanawwa0Nanawwa/dsh-vision-proxyGive a text-only DeepSeek Harness model eyes: a proxy provider that delegates image understanding to any vision-capable model the harness can route, plus vision and vision_config tools.0.1.0-rc.8 (2026-08-20)
dsh-vision-skill0Gingerate/dsh-vision-skill让 DSH 里任何模型（包括 DeepSeek 这类纯文本模型）都能识别图片：识图技能 + 图片发送补丁，装上即用。0.1.1-rc.2 (2026-09-04)
dsh-vision-solution0br1nosense/dsh-vision-solutionDSH 视觉增强方案：识图技能（图片理解/OCR/文档解析）+ 幂等宿主补丁，让纯文本模型也能收发图片。0.1.0-rc.8 (2026-08-20)
dsh-vision-toolkit-mengruoa0mengruoa/dsh-vision-toolkitDeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, OCR, grounding, UI restoration, pixel diff, Artifacts, and Web UI.0.1.1-rc.2 (2026-09-04)
dsh-vision-uachargg0uAcharGG/dsh-vision · npmVision recognition plugin for DeepSeek Harness: paste images into the composer, recognize them via GLM-4V on the host side, and inject the result into the conversation.0.1.0-rc.8 (2026-08-20)
dsh-vision-zoahdev0zoahdev/dsh-visionGive DeepSeek Harness eyes: a vision_analyze tool that sends an image (local path or URL) to an OpenAI-compatible vision model and returns a text description.0.1.0-rc.8 (2026-08-20)
dsh-visionary0zhuiyueya/dsh-visionaryEyes for text-only DeepSeek models: a DeepSeek Harness plugin that transparently converts chat images into OCR text + vision-model descriptions before they reach the LLM. Configure vision backends0.1.1-rc.2 (2026-09-04)
dsh-vlm-bridge0me9rez/dsh-vlm-bridgeDeepSeek Harness (dsh) bundle plugin: vision_analyze tool lets text-only LLM agents read images via SenseNova VLM, with Schemastery config and single-source credentials0.1.0-rc.8 (2026-08-20)
duhai-vision0hamliy-feng/duhai-visionPaddleOCR-VL-first visual model adapter for Codex and DeepSeek Harness0.1.0-rc.8 (2026-08-21)
handwritten-ocr0KL3jd/handwritten-ocrLocal OCR for DSH: handwritten Chinese and math formulas to Markdown with LaTeX. GPU (DirectML) / CPU / NPU backends, settings-driven, one-click install.0.1.1-rc.2 (2026-08-28)
img-preview0dhb861832993-star/img-previewInline image preview for DeepSeek Harness: display local image files (PNG/JPG/WebP/GIF/AVIF/BMP/SVG/ICO/TGA) directly inside the chat — fence language img + img_serve tool. Double-click opens a0.1.0-rc.8 (2026-08-20)
jolly-dsh-vision0JollY-Life/jolly-dsh-visionModLens-style vision bridge for DeepSeek Harness: deepseek-v4-pro as the brain, deepseek-v4-flash-vision-exp as the eyes.0.1.0-rc.8 (2026-08-25)
paste-file-path-pro0lzxcs/paste-file-path-proPasting non-image files into the web composer inserts their paths as @file references (host-side clipboard reading).0.1.1-rc.2 (2026-09-01)
xby-awslabs-aws-diagram0xby-skill/xby-awslabs-aws-diagram通过Amazon Q CLI和MCP服务器在GitHub Codespace中快速生成高质量的AWS架构图。0.1.1-rc.2 (2026-09-01)
xby-image-detect0xby-skill/xby-image-detect检测图像中的80类COCO目标（人、车、动物、日常物品等），输出边界框、置信度和类别标签。0.1.1-rc.2 (2026-09-01)
xby-ocr0xby-skill/xby-ocr兼顾速度与精度的文字识别。输入包含文本的图像，自动检测并识别内容。适用于各类文档、广告牌、屏幕截图等场景。0.1.1-rc.2 (2026-09-01)
xby-ocr-bank-card0xby-skill/xby-ocr-bank-card识别银行卡号、发卡银行和卡类型，使用 Luhn 算法校验卡号有效性。0.1.1-rc.2 (2026-09-01)
xby-ocr-biz-license0xby-skill/xby-ocr-biz-license识别营业执照的统一社会信用代码、名称、法定代表人、注册资本、成立日期、经营范围、登记机关和住所地址。0.1.1-rc.2 (2026-09-01)
xby-ocr-captcha0xby-skill/xby-ocr-captcha输入常见验证码图片，返回验证码文本内容。0.1.1-rc.2 (2026-09-01)
xby-ocr-driver-license0xby-skill/xby-ocr-driver-license识别驾驶证主页（证号、姓名、性别、国籍、住址、出生日期、准驾车型、初次领证日期、有效期限）和副页（档案编号）。0.1.1-rc.2 (2026-09-01)
xby-ocr-handwriting0xby-skill/xby-ocr-handwriting输入包含手写文本的图像，自动检测文本行并识别内容。适用于手写笔记、签名、手写表单等。0.1.1-rc.2 (2026-09-01)
xby-ocr-id-card0xby-skill/xby-ocr-id-card识别身份证正面（姓名、性别、民族、出生日期、住址、身份证号）和背面（签发机关、有效期限），自动判断正反面并校验身份证号有效性。0.1.1-rc.2 (2026-09-01)
xby-ocr-pass0xby-skill/xby-ocr-pass识别港澳通行证、台湾通行证的通行证号码、姓名、性别、出生日期、有效期、签发地点等信息，支持MRZ机读码解析。0.1.1-rc.2 (2026-09-01)
xby-ocr-passport0xby-skill/xby-ocr-passport识别护照号码、中文姓名、英文姓名、性别、国籍、出生日期、签发日期、有效期至、签发地点等信息，支持MRZ机读码解析。0.1.1-rc.2 (2026-09-01)
xby-ocr-pro0xby-skill/xby-ocr-pro高精度文字识别。输入包含文本的图像，自动检测并识别内容。适用于各类文档、广告牌、屏幕截图等场景。0.1.1-rc.2 (2026-09-01)
xby-ocr-vehicle-license0xby-skill/xby-ocr-vehicle-license识别机动车行驶证的号牌号码、车辆类型、所有人、住址、品牌型号、发动机号码、车辆识别代号等信息，支持自动方向检测和主副页过滤。0.1.1-rc.2 (2026-09-01)
zhanzhen0Ya-MiC/zhanzhen湛箴审计OS DSH插件 v2 —— 「审计行业n8n」可视化工作流：拍凭证→OCR→覆核→账套→12规则→报告→CPA签发0.1.1-rc.2 (2026-09-04)