dsh-math-inputZero-token offline math input for DeepSeek Harness: handwriting recognition, screenshot OCR, LaTeX editor, and inline LaTeX rendering.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiaxi626/dsh-math-inputDiscover The Best DSH plugins
1453results
Find image understanding, screenshot analysis and visual interaction plugins; compare inputs and usage.
dsh-math-inputZero-token offline math input for DeepSeek Harness: handwriting recognition, screenshot OCR, LaTeX editor, and inline LaTeX rendering.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:xiaxi626/dsh-math-inputdsh-md-convertConvert Office documents (.doc/.docx/.xls/.xlsx/.ppt/.pptx) and PDFs (incl. scanned, via local OCR) to structurally-formatted Markdown, powered by MarkItDown. CLI + dsh agent tool.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:yakoylp/dsh-md-convertdsh-md-pickerDeepSeek Harness Web GUI 插件:会话输入框 📎 按钮——图片直传官方附件管线;文本类原样暂存;文档(docx/pptx/xlsx/pdf/rtf/odt/epub/csv…)经本地 anydoc 转为 Markdown 后暂存,消息只插图短回执。Composer picker that converts documents to Markdown.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:shangfr/dsh-md-pickerdsh-md-readerDSH Markdown 阅读插件:点击会话中的 MD/图片文件链接时,在浏览器右侧「详情栏」内以真正的三栏布局(侧边栏 | 会话区 | MD 文档)直接渲染阅读,而不是交给系统默认程序。目录 TOC、复制原文、字号缩放、自动跟随磁盘变更、图片内联预览。双半身插件:宿主半身提供只读 HTTP 路由,浏览器半身拦截点击并渲染面板。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wjx-ai/dsh-md-readerdsh-media-forgeMedia Forge: agent + skills workflow for media-generation APIs, with a sidebar panel for loading saved generation skills into a conversation
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Bigesila-B/dsh-media-forgedsh-media-genGenerate images and videos in DSH chat via OpenAI-compatible providers configured in Model settings; dedicated Settings menu and workspace media_gen output.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ant404/dsh-media-gendsh-media-genPlan and execute Atlas Cloud image, video, audio, and 3D workflows in DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:AtlasCloudAI/dsh-media-gendsh-media-guardDeterministic aggregate media budgets and safe request projections for DeepSeek Harness (DSH)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:spyfree/dsh-media-guarddsh-media-inline-previewAll-in-one inline media for DeepSeek Harness chat: ```mip-img / ```mip-video / ```mip-audio fences render images (cards + lightbox + grids, TGA→PNG), native <video> and <audio> players right inside the message (house pattern of img-preview/dsh-mermaid/pbr-render). Image route whole-reads local workspace images; media route streams with HTTP Range seeking and an ffmpeg transcode fallback (cached) for containers browsers cannot play (mkv/avi/flv/wma...). Trust-fenced (loopback + webRuntime.trustedHosts) so LAN/mobile access keeps working. Supersedes the separate img-preview + video/audio fence plugins.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:seeingrain/dsh-media-inline-previewdsh-medomniMedical imaging specialist tools for deepseek-harness: MAIRA-2 and MedGemma report generation for chest X-ray/CT/MRI/retinal (fundus) images, TotalSegmentator organ segmentation, BiomedCLIP zero-shot ultrasound classification, and BiomedParse text-prompted segmentation across X-ray, CT, MRI, ultrasound, and retinal (fundus) images.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bowang-lab/dsh-medomnidsh-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 26 categories.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kagura-agent/dsh-memesdsh-mindmapDeepSeek Harness 思维导图插件:AI 回答自动整理为可编辑 Markdown,支持导出文件和生成图片;核心逻辑已内置,单包发布。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:tuogusa/dsh-mindmapdsh-mindseeDeepSeek Harness 插件:以 MindSee 为后端,为 DeepSeek 提供图片相关能力
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:123cdxcc/dsh-mindseedsh-mingmu明眸 VisionBridge - 自研视觉桥:瞎子模型收图时自动调用视觉模型识别,把识别文字喂回主模型,无感、可配置、升级不丢
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Lab-sku/dsh-mingmudsh-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。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Jack-sun-learner/dsh-minimax-imagedsh-mmroute多模态路由 for DeepSeek Harness:纯文本模型的每一步请求里的每张图片(用户上传 / 工具返回 / MCP 渲染)都先经多模态理解模型转述为文字再作答,图片类报错自动转述重试,两类模型全程交叉协作。Multimodal router for DSH: every image in every step of a text-only model's stream is transcribed to text by a multimodal understander first; image-related failures auto-recover with a transcription retry.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jmxsxwyzjdwl/dsh-mmroutedsh-mmxMiniMax CLI bridge for DeepSeek Harness (dsh): mmx-backed web search fallback and transparent image understanding, with first-run onboarding and a settings card.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:crazyma99/dsh-mmxdsh-mmx-multimodalMiniMax multimodal capability hub for DeepSeek Harness (DSH). One mmx_multimodal tool covers describe/image/video/speech/music/cover/search/quota; optional web_search takeover; built-in client enhancement renders inline players in the Web GUI.
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 context disturbance.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:SHUJILAI/dsh-model-auto-hot-switchdsh-model-autoconfigdsh web 插件:自动配置模型思考档位与能力,并按 provider+model 记住最后选择的思考档位
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wangser10032/dsh-model-autoconfigdsh-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 to the lighter input-only WJZ-P plugin. Works on DSH Web and DSH Desktop.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:lylarcher/dsh-model-capabilitiesdsh-model-capabilitiesExplicit model input-modality selection for the DeepSeek Harness Web UI
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:WJZ-P/dsh-model-capabilitiesdsh-model-managerModel tags, reasoning capabilities, image routing, and vision proxy support for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:hrhgit/dsh-model-managerdsh-model-metadataCapability metadata for hand-declared gateway models, resolved at runtime by bare model name (context window, output cap, reasoning levels, vision) — matched against the official DeepSeek route's catalog, the installed pi-ai catalog, opencode and models.dev, without writing to your settings.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:pgjh/dsh-model-metadataUse a feature keyword or category, then sort by recent updates or GitHub stars.
Read the description, AI analysis and original README to understand what a plugin does.
Review compatibility, dependency ranges and instructions, then copy the available install command.
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.