SEMANTIC DIRECTORY · plugin-directory-semantic-v3-18

Vision Model Bridging & Integration

纳入为纯文本模型透明接入视觉能力的桥接Plugin,以及视觉模型后端、provider、网关、凭据和通道配置等接入基础设施;包括图片拦截后转写、视觉模型路由、按需视觉工具和视觉回退。不纳入面向具体图片或文档内容的识别、解析、转换与结构化产出,也不纳入图像生成、编辑或模型训练。

Use keyword search
Source catalog discovery.composite.2026-09-06.v1-0-5.b92b985e31dfCanonical structure · 823 nodes · 14829 plugins

Leaf membership

50 plugins

@intelligenteyes/dsh@intelligenteyes/dshCatalog AnalyzedIntelligentEyes universal agent vision gateway for DeepSeek HarnessVision & MultimodalnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact1.0.0Evidence updated2026-09-09Public signals46 downloads@limccn/deepseek-vl-support@limccn/deepseek-vl-supportCatalog AnalyzedGive DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.3.0Evidence updated2026-09-08Public signals274 downloads@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 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.0Evidence updated2026-09-09Public signals274 downloadsclaude-vision-mcpEDMOK/claude-vision-mcpCatalog AnalyzedMCP server empowering text-only LLMs with image analysis via any OpenAI-compatible vision APIVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals5 starsDeepSeewindyslime/DeepSeeCatalog AnalyzedDSH-native vision gateway and plugin: routes image turns through pluggable VLM backends while preserving normal DSH text routing.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals6 starsdeepseek-harness-vision-bridgeAsh-b07/deepseek-harness-vision-bridgeCatalog AnalyzedExperimental vision bridge for text-only DeepSeek models in DeepSeek Harness.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdeepseek-harness-vision-pluginsjscy05/deepseek-harness-vision-pluginCatalog AnalyzedDSH plugin from sjscy05/deepseek-harness-vision-pluginVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdeepseek-visionaryxlight/deepseek-visionaryCatalog Analyzed使用 DeepSeek 官方多模态视觉模型让你的 Agent 不再眼瞎(支持 DSH、Zed、OpenCode、Codex、Claude Code、Cursor、Claude Desktop)Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals18 starsdsh-deepseek-visiondsh-deepseek-visionCatalog AnalyzedA vision-language gateway provider route: pasted images are described by a configurable VL model (Qwen-VL by default) before the DeepSeek wire.Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.7Evidence updated2026-09-06Public signals9 stars · 3495 downloadsdsh-deepseek-vision-routermochgolf/dsh-deepseek-vision-routerCatalog AnalyzedTransparent image preprocessing route for DeepSeek HarnessVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-doubao-pluginPractice019/dsh-doubao-pluginCatalog AnalyzedDSH Plugin:通过本地 Quicker 转发(doubao web2api) 提供 `doubao_ask` 动态搜索/图片生成/多模态识图工具, 并支持**粘贴图片 → 本地路径**(paste-to-path)。UI EnhancementsGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-easyvisions3yf1337/dsh-easyvisionCatalog AnalyzedGive text-only models vision: a describe_image tool that delegates images to a vision model from your dsh model list over the harness's own LLM runtime.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-eyesLeeminjing/dsh-eyesCatalog AnalyzedOn-demand vision for text-only DeepSeek models: upload images, and the model calls a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-image-bridgehZsFN/dsh-image-bridgeCatalog AnalyzedImage message bridge for text-only models in DeepSeek Harness (dsh): image blocks → text placeholder + local path, vision via qwen scriptVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-image-dscribershuxu-zhao/dsh-image-dscriberCatalog AnalyzedGiving text models eyes.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-image-to-textHiSeax/dsh-image-to-textCatalog AnalyzedDSH plugin: lets text-only (non-multimodal) models send and read images — bypasses the image admission gate, rewrites image blocks to local paths, and OCRs/describes them via configurable vision API providers (image_to_text tool).Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-image-unlockFrostLeafKEE/dsh-image-unlockCatalog AnalyzedDeepSeek Harness Plugin:解除 Web GUI 图片输入限制,图片附件文本化后交给 vision skill 识图 | dsh plugin that lifts the image-input gate and hands attachments to a vision skillVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-image-vision-bridgeIcestab/dsh-image-vision-bridgeCatalog AnalyzedDSH Plugin:聊天发图自动交给视觉模型 (mimo-v2.5) 分析,把文本描述悄悄喂给纯文本主模型,聊天记录保持原图显示。Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 stars

Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.