Plugins
The complete directory supports discovery. Quality dimensions are shown separately; automated analysis does not prove feature completeness. The plugin manager continues local inspection.
Found 1065 source candidates (configured-source coverage 15812 / 15812) · snapshot: 2026-09-19Search order: text relevance first + bounded quality evidence
dsh-image-viewerdsh-image-viewerCatalog AnalyzedUpgrades DSH image viewing with pointer-centered zoom, pan, galleries, downloads, keyboard support, and inline region notes.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.2aura-visionaura-visionCatalog AnalyzedFree vision OCR with adaptive tile recognition for long documents and Markdown/Word/PNG/Excel export.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.0.2dsh-plugin-image-toolsdsh-plugin-image-toolsCatalog AnalyzedDSH 图片Plugin，三个工具覆盖三种场景：ask_user_choice 图片/图文混合选择卡（Web GUI 渲染，可放大查看）+ show_images 回复内嵌图片（图文混排）+ save_received_images 盲模型收图存为工作区文件；聊天栏所有图片点击放大，支持滚轮缩放与拖拽平移。Source支持本地路径 / http(s) URL / base64 data URI。零 token 本地渲染，纯Plugin实现不改核心包。Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.6.8dsh-plugin-vision-toolkitdsh-plugin-vision-toolkitCatalog AnalyzedVision toolkit for DeepSeek Harness -- glance, ground, detect, crop CLI tools for text-only agents to understand imagesVision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.1dsh-siliconflow-visiondsh-siliconflow-visionCatalog AnalyzedDSH Plugin：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。含持久化的粘贴识别面板（web 端）。Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.1.1@dsh-extension/dsh-vision-bridge@dsh-extension/dsh-vision-bridgeCatalog AnalyzedOn-demand vision for text-only DSH sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision modelVision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.0.0dsh-tool-accurate-visiondsh-tool-accurate-visionCatalog AnalyzedModel-facing accurate_vision tool: precise image spatial reasoning via a vision modelVision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0dsh-image-generationdsh-image-generationCatalog AnalyzedConfigure multiple image providers in Settings and call image_generate with the one selected model; images save under generate/image and show inline in the conversation.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.1@try-works/dsh-vision-worker@try-works/dsh-vision-workerCatalog AnalyzedDeepSeek Harness plugin: a vision worker over Cloudflare Workers AI (@cf/moonshotai/kimi-k2.6) that routes image requests from text-only callers, returns a versioned righthand.vision.v1 envelope, and supports follow-up questions.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.1@zzdream67/dsh-vision-bridge@zzdream67/dsh-vision-bridgeCatalog AnalyzedLet text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0dsh-composer-image-toolsdsh-composer-image-toolsCatalog Analyzed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。Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0@acc1143/dsh-vision-bridge@acc1143/dsh-vision-bridgeCatalog AnalyzedDSH 双模型路由Plugin：主对话留在 DeepSeek，图片任务自动分发到显式配置的视觉模型，再把分析结果交回 DeepSeek 继续。Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.1easy-visioneasy-visionCatalog AnalyzedA 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 text description produced by a separate OpenAI-compatible vision modVision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.1dsh-visiondsh-vision-webCatalog AnalyzedVision for text-only DeepSeek via Doubao Web by default (zero-cost, no API key — drives your logged-in Chrome through a Windows CDP bridge), with Antigravity IDE quota (flash/pro) or Gemini fallback; auto detail escalation, vision evidence memory with compaction rehydration, content-hash cache, and a bilingual client panel.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifact0.1.0dsh-image-guarddsh-image-guardCatalog AnalyzedTrims historical images in outgoing chat requests down to a recent-image count, learns the provider per-prompt image cap from HTTP 400 responses, and retries with fewer images so image-heavy sessions keep working.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.8.17dsh-computer-use-visiondsh-computer-use-visionCatalog AnalyzedWindows computer-use capability for DeepSeek Harness: screenshot → vision model → simulated mouse/keyboard input, with self-evolving knowledge base.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifact0.1.1dsh-bundle-visiondsh-bundle-visionCatalog AnalyzedVision bundle + plugin for DeepSeek Harness: the describe_image tool reads local images and asks any configured multimodal route, with zero core changesVision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifact0.1.0dsh-vision-autoswitchdsh-vision-autoswitchCatalog AnalyzedDeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.2Source candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation