SEMANTIC DIRECTORY · plugin-directory-semantic-v3-18
In-Chat Media Display & Input
在对话界面中展示或注入媒体：图片、画廊、音视频预览、内联 HTML/SVG/CSV 卡片、表情包、图片上传和图床外链等。不负责理解、生成或管理完整媒体素材库。
Leaf membership
50 plugins
@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 modelCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact1.0.0Evidence updated2026-09-09Public signals444 downloads@jetecho/dsh-csv-and-image-preview@jetecho/dsh-csv-and-image-previewCatalog AnalyzedPreview images / SVG and CSV tables in the DeepSeek Harness chat, rendered as real browser <img> / <table> elements. Preview-first workflow: show the user the asset, wait for approval, then apply the real change.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.2Evidence updated2026-09-09Public signals266 downloadsagent-vision-toolkitAnionex/agent-vision-toolkitCatalog Analyzed为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCodeCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1163 starsDeepSeek-Harness-biaoqingbaomoononnn/DeepSeek-Harness-biaoqingbaoCatalog AnalyzedSticker/emoji expression for assistants: emotion-driven auto-matching, library management, AI image tagging, dialects, style mimicry, and chat-based tag refinement.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdock-imagesdock-imagesCatalog AnalyzedImage viewer for the dock workbench: PNG, JPEG, GIF, WebP, BMP, SVG, ICO and AVIF, with SVG rendered as image data only.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.1Evidence updated2026-09-07Public signals4 stars · 248 downloadsdsh-autovision@iroam2375/dsh-autovisionCatalog AnalyzedVision for text-only dsh models: paste an image and a configured multimodal model transcribes it to text automatically — transparent twin routing, an agent-callable read-image tool, no built-in keys or relay.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.0Evidence updated2026-09-07Public signals1 stars · 211 downloadsDSH-dseyesdsh-dseyesCatalog AnalyzedNative image attachments for text-only DeepSeek in the Web GUI: pasted or dropped images appear as thumbnails in the session, and before dispatch the host reads them with the free Zhipu GLM-4V-Flash vision API (glm-4v-flash fallback chain) and substitutes the description, so DeepSeek answers about the image while the original is kept in history.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.2.0Evidence updated2026-09-07Public signals3 stars · 401 downloadsdsh-ext-vision-proxyjin123-alpha/dsh-ext-vision-proxyCatalog AnalyzedExternal vision proxy extension for DeepSeek Harness, enabling text-only models to analyze and understand images via OpenAI-compatible vision APIs.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-image-inlinecondaThinker/dsh-image-inlineCatalog AnalyzedDSH plugin: show_image tool that renders an image inline into the web chat flow (QQ/WeChat style) — path text in the message, image bytes never enter model context.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-image-mmxfengs2021/dsh-image-mmxCatalog Analyzed给 DSH 文本模型装眼睛：图片自动调用 mmx（MiniMax VLM）识别，识别结果注入模型上下文CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-image-previewywleeo/dsh-image-previewCatalog Analyzed让 DeepSeek Harness (dsh) 对话正文直接显示本地图片的Plugin：本地路径自动内联为图片 + 可点击的本地地址行CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-image-previewReiRui/dsh-image-previewCatalog AnalyzedDSH plugin from ReiRui/dsh-image-previewCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-image-to-pathcesaryike/dsh-image-to-pathCatalog AnalyzedDSH Plugin:让纯文本模型对话也能拖图/贴图——图片自动保存到会话工作区,以文件路径交给模型(多模态模型不受影响)CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-image-visionxsoc1/dsh-image-visionCatalog AnalyzedChat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud): pasted/dropped images become `view_image` path markers before reaching text-only DeepSeek models.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-media-carddsh-media-cardCatalog AnalyzedShow local images or short videos in the current DeepSeek Harness conversation card, with click-to-preview and a download link. Works over local and remote connections.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.3.0Evidence updated2026-09-08Public signals140 downloadsdsh-mmroutejmxsxwyzjdwl/dsh-mmrouteCatalog AnalyzedTransparent multimodal routing for text-only models: every image in every model call is fully transcribed (verbatim OCR, data, uncertainty zones, injection-hardened) by your own multimodal understander, with focused re-look via vision_relook and automatic retry on image-related failures. No bundled endpoints, no borrowed logins.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsDSH-Multimodalyauntyour/DSH-MultimodalCatalog AnalyzedDSH 多模态输入Plugin：为不同类型的文件（图片 / 视频 / 音频 / 文本）配置独立的处理模型链，在文件进入会话模型之前，先用预设模型把它处理成 Prompt Tokens（文本），再交给会话模型。Plugin在 DSH 设置中新增独立的 Multimodal 页面。CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-photosjohndfowler/dsh-photosCatalog AnalyzedDSH plugin from johndfowler/dsh-photosCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 stars
Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.