插件目录
完整目录用于发现；各质量维度分别展示，自动化分析不代表插件功能已经完整验证。插件管理器会在本地继续检查候选源。
找到 2128 个来源候选（配置来源覆盖 15812 / 15812） · 快照：2026-09-19搜索排序：文本相关性优先 + 有界质量证据修正
dsh-anydoc-markdownSeerableOfficial/dsh-anydoc-markdown目录 已分析Document → Markdown + vision image description plugin for DeepSeek Harness (dsh). Converts Word/PPT/Excel/ODT/RTF/EPUB/CSV/PDF via firecrawl-anydoc and describes embedded images with a VLM.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析SuperMate-Harness-SystemSuperMate-Ai/SuperMate-Harness-System目录 已分析Give DeepSeek Eyes · 给 DeepSeek 装眼睛 — a DeepSeek Harness (DSH) Skill: local vision models or vision APIs let DeepSeek read images and graphic files视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-modlensYZz-S/dsh-modlens目录 已分析DeepSeek Harness (dsh) vision plugin — a fork of ModLens adding multi-engine image reading (Gemini, Volcengine Ark/Doubao, Claude) with per-call engine selection.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-v4flash-tilerdoublehappy123/dsh-v4flash-tiler目录 已分析DSH plugin: auto-tiles oversized chat images into labelled grid tiles for DeepSeek v4Flash vision, with Python tiling engine视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-agnes-omniwumu1111111/dsh-agnes-omni目录 已分析Agnes omni-modal plugin for DeepSeek Harness: agnes_vision (image understanding) + agnes_image (text-to-image / image-to-image) + a vision bridge that lets you send images in chat. API key via DSH credentials, never in code.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-plugin-chat-enhancesupanexus/dsh-plugin-chat-enhance目录 已分析Searchable model picker with recent chips, vision capability tags, and composer image upload for DeepSeek Harness.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析taxue-dsh-artisantaxueseek/taxue-dsh-artisan目录 已分析DSH 一体化视觉创作工具链：提示词反推与审计优化，多供应商生图，支持异步后台出图。视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-rich-artifactsInkotake/dsh-rich-artifacts目录 已分析DeepSeek Harness Artifact/Deliverable plugin: publish workspace files as chat artifacts with inline image previews and download cards.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-imggmleong/dsh-img目录 已分析Give text-only models eyes: analyze_image tool for DeepSeek Harness, backed by free Chinese vision APIs (GLM-4V-Flash / Qwen-VL) or any OpenAI-compatible endpoint. 给纯文本模型装上眼睛的 dsh 插件。视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-upload-buttonvictorytianyi-dev/dsh-upload-button目录 已分析DeepSeek Harness Web UI 图片上传插件 + DashScope 文生图工具 | Upload-image button plugin for DSH Web UI + text-to-image helper视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-product-previewchoco9527/dsh-product-preview目录 已分析以访达式分栏浏览对话节点中的本地图片、视频与 SVGA 产物。UI 增强GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-computer-use-winsecretxuan/dsh-computer-use-win目录 已分析Native-vision Windows computer-use for DeepSeek Harness: screenshots, UIA, OCR, and approval-gated input视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-screenshotXEsx630/dsh-screenshot目录 已分析WeChat-style screenshot for the DeepSeek Harness composer: capture the screen (optionally hiding the DSH window), drag-select a region, and attach the image directly to the message. Windows + PowerShell server-side crop.记忆GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-comfyuidsh-comfyui目录 已分析让 DeepSeek Harness 的 Agent 直接驱动本地或远程 ComfyUI：comfyui_run / comfyui_object_info / comfyui_workflow 工具生成与编辑图像、视频，附带工作流库（图工作流提取：按分量 / 主流程 / 整体）、加载区分辨率自动匹配、实时队列、SDXL 与 Wan 2.1 模板、配套 skill 与同源媒体代理。视觉与多模态npmGitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计有限审计报告 0 项制品0.5.1dsh-vlm-bridgeme9rez/dsh-vlm-bridge目录 已分析DeepSeek Harness (dsh) bundle plugin: vision_analyze tool lets text-only LLM agents read images via SenseNova VLM, with Schemastery config and single-source credentials视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-desktopnihaozyj7/dsh-desktop目录 已分析Go + Wails desktop shell for DeepSeek Harness: native window, engine supervision, self-update, and preview source builds视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析adatile-mcpMutton-hub/adatile-mcp目录 已分析AdaTile-MCP: high-resolution image adaptive tiling MCP server for DeepSeek vision model (deepseek-v4-flash-vision-exp). L1-L6 pipeline (fastpath, saliency, adaptive tiling, Files API assembly, streaming VLM, rule-based merge) + eval harness. Setup: clone, run setup.bat, add your agent MCP config -> see README.视觉与多模态GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析dsh-plugin-visionaijunjiang/dsh-plugin-vision目录 已分析Give your DSH agent eyes via any OpenAI-compatible vision model - 11 provider presets (Doubao/Qwen-VL/GLM-V/OpenAI/Gemini/Ollama...), capability checkboxes that inject live prompt guidance, and analysis of images the user drops into the chat; the agent writes its own observation prompt, and base64 never enters its context.记忆GitHub兼容性DSH 0.1.6-alpha.2 · web依赖审计未测试制品未解析来源级候选描述来自第三方目录及 Registry 复核的公开来源，属于不可信导入文本安装前仍需本地 inspect / plan / confirm