SEMANTIC DIRECTORY · plugin-directory-semantic-v3-18
Image Understanding & Analysis
让模型理解已有图片内容并输出语义结果：图像描述、视觉问答、截图或界面分析、物体与场景识别、图像比较及视觉模型桥接。不含以文字提取为核心的 OCR、确定性图像处理、屏幕采集与图像生成。
Leaf membership
51 plugins
dsh-pseudo-visionDDDFXYqiming/dsh-pseudo-visionCatalog AnalyzedLocal OCR, color-statistics, pixel-scan, and metadata bridge for text-only DeepSeek Harness models; no external vision API.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-read-imageOoWJZZoO/dsh-read-imageCatalog AnalyzedA plug-and-play image-reading plugin for DeepSeek Harness. After installation, DSH will no longer refuse to feed images into sessions with pure-text models; instead, the image will be mapped as [Image #N] in the session. The Agent can then invoke tools on its own to read images from the session or from specified paths.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-Sightcransmathenia666-hash/dsh-SightCatalog AnalyzedGive text-only DeepSeek Harness (dsh) agents vision — pasted images auto-convert to text descriptions with persistent caching, each image converted only once.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-tool-visiongloryxpnv/dsh-tool-visionCatalog AnalyzedLocal-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-tool-vision-readMappedinfo/dsh-tool-vision-readCatalog AnalyzedDSH plugin: vision_read — route image reading to a dedicated vision model (e.g. Kimi K3) so text-only agents can see imagesCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-view-imagejohnoooooo/dsh-view-imageCatalog Analyzed让 dsh 用独立的 OpenAI 兼容视觉模型读图：纯文本路由下粘贴图片自动改写为附件标记，聊天流内联显示图片（右对齐缩略图/点击放大/Copy/拖拽），主对话历史只保留纯文本描述CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-visionjoyiok/dsh-visionCatalog AnalyzedDSH plugin: image_analyze tool that sends screenshots/photos to an OpenAI-compatible vision modelCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-vision-bridgeXieweikang123/dsh-vision-bridgeCatalog AnalyzedGive a text-only dsh model eyes: pasted images recognized into text via an OpenAI-compatible vision endpoint.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-vision-bridgeTwistedRiCen/dsh-vision-bridgeCatalog AnalyzedDSH-native Vision Evidence bridge for text-only reasoning models with native image attachments and strict multi-image validation.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-vision-guarddsh-vision-guardCatalog AnalyzedTransparent image guard for text-only routes: paste images without the 400 session deadlock, plus a vision_analyze tool for OCR/PDF/docx/pptx/video.CompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.3Evidence updated2026-09-07Public signals1 stars · 785 downloadsdsh-vision-helperYuuz12/dsh-vision-helperCatalog AnalyzedDeepSeek Harness Vision Helper/DeepSeek Harness 视觉辅助方案CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-vision-ocrwangxiang0605qvq/dsh-vision-ocrCatalog AnalyzedDSH 图片识别Plugin：输入框一键选图发送识别Request（需自备支持图像输入的模型与 API Key）CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-vision-pluginbug-huntter/dsh-vision-pluginCatalog AnalyzedConfigurable image recognition for text-only DSH models: image messages are first transcribed by any OpenAI-compatible vision model (Base URL, model ID and key configured in a Settings section), then passed to the main model as text; image-input support is advertised while enabled.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signalsNo public usage signalsdsh-vision-pluginzcma11/dsh-vision-pluginCatalog AnalyzedDeepSeek Harness plugin: upload/paste images; on send transcribe via a vision model (DashScope) or offline Windows OCR. 用deepseek-harness做的，Made with the DeepSeek-harness.CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-vision-pluginwoyeshishen/dsh-vision-pluginCatalog AnalyzedDSH plugin from woyeshishen/dsh-vision-pluginCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-vision-pluginld-1101/dsh-vision-pluginCatalog AnalyzedGive your text-only model eyes - chat image attachments are auto-described via a vision model (default prompt), with iterative re-parsing through model-generated prompts when details are missing; system/custom model modes + GUI config panel, key-safe secret handling, and a small host patch for DSH 0.1.0-rc.6 (see repo README).CompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-vision-routerdsh-vision-routerCatalog AnalyzedFree vision for text-only agents: built-in keyless vision chain plus pixel tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots); paste an image to use it.CompatibilityDSH 0.1.2-rc.1 · webDependency audit1 reported in bounded auditArtifact2.1.2Evidence updated2026-09-06Public signals1070 stars · 51307 downloadsdsh-vision-skillGingerate/dsh-vision-skillCatalog Analyzed让 DSH 里任何模型（包括 DeepSeek 纯文本模型）都能识别图片：识图技能 + 幂等宿主补丁，装上即用 / Let every DSH model see images: vision skill + idempotent host patch.CompatibilityDSH 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.