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
@gz2016/dsh-plugin-image-picker@gz2016/dsh-plugin-image-pickerCatalog AnalyzedAdds a file-picker 'attach image' button to the composer toolbar, since DSH's own web client only supports paste and drag-and-drop for image attachments (v1 scope, per its own upstream design notes) - a real gap for touch devices with no drag-and-drop andMemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0dsh-screenshotdsh-screenshotCatalog AnalyzedScreenshot toolkit for dsh - name reserved; first release in development.Tools & CapabilitiesnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifact0.0.1dsh-vision-completeYts1919/dsh-vision-completeCatalog Analyzed给 DeepSeek 补上「眼睛和耳朵」的多模态视觉Plugin：看图 / OCR / 物体检测 / 视频理解 / 语音转写 / 截图直读，一键安装（DSH Plugin）。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-visionwilliam-jin-cmu/dsh-visionCatalog Analyzeddsh Plugin：给纯文本 DeepSeek 加视觉——view_image 工具桥接任意 OpenAI 兼容 VLM（默认智谱免费档，实测 4 厂商 10 模型）Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-web-ui#dsh-tool-describe-imageDamonKoy/dsh-web-uiCatalog AnalyzedGives a text-only model image understanding via a vision-language model, exposed as a `describe_image` tool.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-plugin-describe-imagewhitelonng/dsh-plugin-describe-imageCatalog AnalyzedDeepSeek Harness plugin: describe_image — give a text-only model vision through an OpenAI-compatible VLM endpointVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedclaude-vision-mcpEDMOK/claude-vision-mcpCatalog AnalyzedMCP server empowering text-only LLMs with image analysis via any OpenAI-compatible vision APIVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-plugin-visiontdf1995/dsh-plugin-visionCatalog AnalyzedVision for text-only LLMs in DeepSeek Harness (DSH): describe images / OCR / VQA via free Gemini & GLM vision APIsVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-image-bridgekbpoyo/dsh-image-bridgeCatalog AnalyzedDSH Plugin：让纯文本模型也能看图。Web 端直接粘贴图片即可发送，无需指定图片路径；模型自主调用视觉技能查看，多模态模型原生直通，零skill绑定。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedds-vision-pluginSorwcyra/ds-vision-pluginCatalog AnalyzedPaste images into DeepSeek Harness with a four-model vision race, OCR, and an automatic text bridge.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-vision-hubxing666173/dsh-vision-hubCatalog AnalyzedDeepSeek Harness EAC 视觉全家桶:15 个像素级视觉工具(增强版 dsh-tool-vision)+ 桥接内联预览 + 拖拽文件上传,单端点驱动,对话干净,EAC 原生设置适配Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-plugin-vision-bridgec-ling/dsh-plugin-vision-bridgeCatalog Analyzed【已停止维护】DeepSeek Harness 视觉桥接Plugin：新版 Harness 已原生支持图片识别，请使用原生能力，本仓库仅作历史参考。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedmeow-visionmeimiaoji-creator/meow-visionCatalog Analyzedmeow-vision 是 DeepSeek Harness 的一款视觉Plugin，解决纯文本模型无视觉。另一方面vue页面开发视觉验证不闭环的问题。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-visionreimu-create/dsh-visionCatalog AnalyzedDSH plugin: text-only models (e.g. DeepSeek-V4) automatically see images via a vision model. Official surface-replace, cache-friendly, human transcript untouched. 纯文本模型自动识图桥Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-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.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-vision-helperYuuz12/dsh-vision-helperCatalog AnalyzedDeepSeek Harness Vision Helper/DeepSeek Harness 视觉辅助方案Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-visionxiaoshihou514/dsh-visionCatalog AnalyzedNative vision capability extension, using either Zhipu (free) or Qwen-VL (local).Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedtext-llm-visionshaoqiuyuavailable/text-llm-visionCatalog AnalyzedScene-aware vision routing layer for DeepSeek Harness (dsh): decides which engine/backend an image should go to (chat/UI/table/code) before other vision plugins route it. Switch-gated, front-loaded, never touches other plugins' tools. 场景级识图路由层。Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedSource candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation