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 2128 source candidates (configured-source coverage 15812 / 15812) · snapshot: 2026-09-19Search order: text relevance first + bounded quality evidence
dsh-image-toolsJuneLearn/dsh-image-toolsCatalog AnalyzedDeepSeek Harness 多服务图片生成与编辑Plugin，支持 OpenAI Images、Gemini Interactions 与顺序故障转移。Multi-provider image generation and editing for DeepSeek Harness.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-visionzoahdev/dsh-visionCatalog AnalyzedGive DeepSeek Harness eyes: analyze images with an OpenAI-compatible vision model via a vision_analyze tool.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-vision-bridgelium970320/dsh-vision-bridgeCatalog AnalyzedDSH 视觉桥接Plugin：让无视觉能力的主模型看图（会话收图 + 自动转文字 + view_image 工具）Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-vision-toolvisail/dsh-vision-toolCatalog AnalyzedPaste an image into the chat box and text-only DSH models can "see" it — auto-rewrite of pasted images + analyze_image tool routed to a Kimi vision model.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-tool-image-recognizeLuRia-yzk/dsh-tool-image-recognizeCatalog Analyzedimage_recognize tool for DSH: give text-only models vision via qwen3-vl-flashVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedimg-previewdhb861832993-star/img-previewCatalog AnalyzedInline local image preview for DeepSeek Harness - img_serve tool + img fence, renders PNG/JPG/WebP/GIF/AVIF/BMP/SVG/ICO directly in chat.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-vision-bridgeAbdullahElTiby/dsh-vision-bridgeCatalog AnalyzedVision bridge for text-only models (DeepSeek, pi-ai routes): Gemini Flash describes attached images at the llm stream seam and provides a describe_image tool.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-official-visionwilianyichen/dsh-official-visionCatalog AnalyzedDirect official DeepSeek vision API bridge for DeepSeek Harness: deepseek-v4-flash-vision-exp provider route. 直连 DeepSeek 官方视觉 API 的 DSH PluginVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-gpt-imageCAI-MH/dsh-gpt-imageCatalog AnalyzedGenerate images through a logged-in web ChatGPT session and download them to a local directory.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedauto-visionh-k-c/auto-visionCatalog AnalyzedDeepSeek Harness 图片Plugin：贴图不会让对话报错，模型自动判断是否需要看图（支持智谱/魔搭免费视觉模型，图片在聊天窗口正常显示）Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-generation-imagesfyyy/dsh-generation-imageCatalog Analyzeddsh 中可以使用Plugin来调用gpt-image2生成图片Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-see-imagetiefeiyu/dsh-see-imageCatalog AnalyzedA see_image vision tool plugin for DeepSeek Harness — describe images through any OpenAI-compatible vision model (GitHub Copilot, OpenAI, Ollama, vLLM, LM Studio).Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-llm-vision1710782766/dsh-llm-visionCatalog AnalyzedReliable vision + OCR for text-only models on DeepSeek Harness: describe_image (normal/critical) + extract_text tools, auto-preprocessing, retries, and a persistent answer cache.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-tool-visionwanshichenguang/dsh-tool-visionCatalog AnalyzedModel-facing image_describe (识图) tool over the DashScope OpenAI-compatible API (qwen3.7-flash), plus a paste bridge: on text-only sessions, pasted images auto-convert to file paths at send time and render back in the transcript, so they never trip image admission. Bring your own DASHSCOPE_API_KEY; endpoint/model/budgets configurable, redirect-proof HTTP client, works in every agent preset.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-pro-visionlasdrder0705/dsh-pro-visionCatalog AnalyzedDSH plugin: let DeepSeek-V4-Pro use V4-Flash-Vision-Exp for attached images. Install: dsh plugin --profile web add github:lasdrder0705/dsh-pro-visionVision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-image-zoomTianyiTwT/dsh-image-zoomCatalog Analyzed**Smart image splitting and zooming for Vision-Language Models (VLMs) inside [DeepSeek Harness (dsh)](https://github.com/deepseek-ai/deepseek-harness).**Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-tool-visionTNTsama11/dsh-tool-visionCatalog AnalyzedDeepSeek Harness (DSH) plugin that lets a text-only agent call DeepSeek-V4-Flash-Vision-Exp to see images on demand, without manually switching models.Vision & MultimodalGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-image-uckkkuckkk/dsh-image-uckkkCatalog Analyzed@{name=dsh-image-uckkk; version=0.1.0; description=图片处理：读取图片尺寸/格式、缩放与格式转换（内置 ffmpeg，跨平台）; type=module; main=lib/index.js; exports=; files=System.Object[]; dsh=; dependencies=; keywords=System.Object[]; author=istone <ad571@qq.com>; license=MIT; peerDependencies=}.descriptionVision & 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
