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

OCR & Document Recognition

从图片、截图、扫描件、PDF 或文档中提取文字、公式和结构化字段,包含手写、证件、票据、表格、二维码与条码识别,输出文本、Markdown、坐标或文档结构。不含开放式视觉问答。

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

Leaf membership

52 plugins

dsh-plugin-mm-visionElohia/dsh-plugin-mm-visionCatalog AnalyzedSynesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-plugin-visionqizhen2021/dsh-plugin-visionCatalog AnalyzedDSH plugin from qizhen2021/dsh-plugin-visionVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-plugin-visionco-Elly/dsh-plugin-visionCatalog Analyzed👁️ Give your DeepSeek Harness the gift of sight — enables pure-text LLMs to analyze images via Zhipu's free GLM-4V-Flash vision modelVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-qr-toolkitdsh-qr-toolkitCatalog AnalyzedQR code & barcode toolkit for DeepSeek Harness: decode images (PNG/JPEG, local or URL) and generate QR codes as PNG. 二维码/条码工具箱:解码与生成。Vision & MultimodalnpmGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency audit0 reported in bounded auditArtifact0.1.1Evidence updated2026-09-08Public signals333 downloadsdsh-tool-describe-imagesala003/dsh-tool-describe-imageCatalog AnalyzedDSH plugin from sala003/dsh-tool-describe-imageVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals5 starsdsh-tool-ocrferstar/dsh-tool-ocrCatalog Analyzed本地 OCR Plugin:让纯文本生成 LLM 也能读懂图片 | Local OCR plugin: give text-only generative LLMs the ability to read imagesVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-tool-visionScorp1o117/dsh-tool-visionCatalog AnalyzedSend local images or HTTP(S) image URLs to a configured OpenAI-compatible vision endpoint with the inspect_image tool and return its text response to the conversation.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signalsNo public usage signalsdsh-umi-ocr-visionpaul-yangmy/dsh-umi-ocr-visionCatalog AnalyzedDSH plugin from paul-yangmy/dsh-umi-ocr-visionVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals0 starsdsh-Unlimited-OCR-SkillAidenwu0209/dsh-Unlimited-OCR-SkillCatalog AnalyzedUnlimited-OCR for DeepSeek Harness with a native tool and GUI configurationVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-visionxzyonline/dsh-visionCatalog AnalyzedVision for text-only DeepSeek: view_image tool via any OpenAI-compatible VLM endpoint. macOS/Windows/Linux, one-click install.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-visionzoahdev/dsh-visionCatalog AnalyzedGive DeepSeek Harness eyes: analyze images with an OpenAI-compatible vision model via a vision_analyze tool.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals1 starsdsh-vision-bridgeximengxiaolan/dsh-vision-bridgeCatalog AnalyzedComposer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals3 starsdsh-vision-edge-doubaoiceBear662/dsh-vision-edge-doubaoCatalog AnalyzedDeepSeek Harness(DSH)视觉Plugin:Edge+豆包网页版识图,零成本免 API Key。通用识图 + 数学建模图专项(几何/流程图/图表/表格/公式)+ 不确定项澄清闭环。Vision plugin for DeepSeek Harness: image understanding via Edge + Doubao Web, zero cost, no API key. General recognition + math-modeling diagrams (geometry/flowcharts/charts/tables/formulas) + clarify loop for uncertainties.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-vision-mcpmoton16/dsh-vision-mcpCatalog AnalyzedGive your text-only LLM eyes: zero-dependency MCP server that reads images via external OpenAI-compatible vision models with automatic provider fallback, plus a one-command patch for DSH image-attachment degradation.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-vision-primitiveszouyuanqing/dsh-vision-primitivesCatalog AnalyzedNative interactive visual-reasoning plugin for DeepSeek Harness: precise pixel grounding (SOM grid / zoom / annotate / measure / diff / color / OCR) + MiMo V2.5 multimodal backend, zero external MCP servers.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-vision-routernlqh7/dsh-vision-routerCatalog Analyzed给 DeepSeek Harness 纯文本模型加视觉:采用codex风格聊天框拖图自动分流给用户配置的视觉模型转文字,v4 不切换模型即可识图。 Vision for text-only DSH models: routes chat-box images to a user-configured vision model and returns text descriptions, deepseek-v4-pro reads images without switching.Vision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals2 starsdsh-vision-sidecar121103qwq/dsh-vision-sidecarCatalog AnalyzedHosted free vision sidecar for DeepSeek Harness with durable session evidenceVision & MultimodalGitHubCompatibilityDSH 0.1.2-rc.1 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-10Public signals5 starsdsh-vision-skillDDDFXYqiming/dsh-vision-skillCatalog AnalyzedVision skill plugin for DeepSeek Harness (image analysis and OCR)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.