SEMANTIC DIRECTORY · plugin-directory-semantic-v3-19
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。
Leaf membership
53 plugins
@gelomen/glm-vision-plugin@gelomen/glm-vision-pluginCatalog AnalyzedDSH Web Plugin：调用智谱 GLM 视觉模型分析图片（analyze_image 工具 + Plugin设置卡片）。CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.0Evidence updated2026-09-25Public signals595 downloadsaura-visionaura-visionCatalog AnalyzedFree vision OCR with adaptive tile recognition for long documents and Markdown/Word/PNG/Excel export.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.0.2Evidence updated2026-09-22Public signals1 stars · 708 downloadsDeepSeek_PrismYOGEMOW/DeepSeek_PrismCatalog Analyzed为纯文本模型按需识图：DSH 零补丁 Cordis Plugin（prism_see 工具 + 图片 VEP 降级 + 技能运行时注册）+ Codex Skill；多 Provider 视觉 API，VEP/1 低 Token 视觉证据包CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals5 starsdoc-ocrjiawood2006/doc-ocrCatalog AnalyzedLocal OCR for PDFs/scans/images using macOS Vision. 本地OCR文档识别。CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 starsdsh_image-modlens-bridgewendou-chen/dsh_image-modlens-bridgeCatalog AnalyzedDSH plugin: for text-only model routes, save uploaded images under .dsh_images and analyze them via modlens (external vision provider), replacing the image block with text evidence.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 starsdsh-codex-mediabinsarjr/dsh-codex-mediaCatalog AnalyzedImage & document analysis tools for DeepSeek Harness, powered by a local OpenAI Codex CLI (zero deps, 3 transports, pairs with dsh-drop-to-path)CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals1 starsdsh-deepseek-visionArgonaut790/dsh-deepseek-visionCatalog AnalyzedImage understanding, OCR, and persistent visual evidence for text-only DeepSeek Harness modelsCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals2 starsdsh-deepseek-visionCheng-cheng9669/dsh-deepseek-visionCatalog AnalyzedReuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool drives the local deepseek-vision-cli browser automation (manual login helper, deep-think enabled, auto-closes browser) and returns image descriptions as text.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals1 starsdsh-eye-visionAlloyPlane/dsh-eye-visionCatalog AnalyzedDSH plugin from AlloyPlane/dsh-eye-visionCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals2 starsdsh-image-pathifydsh-image-pathifyCatalog AnalyzedLets text-only models handle pasted chat images, with a native vision experience, batch image viewing, and a built-in OpenAI-compatible analyze_image tool; vision-capable models are unaffected.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.9Evidence updated2026-09-20Public signals4 stars · 3360 downloadsdsh-image-toolsxiaoxianyu-office/dsh-image-toolsCatalog AnalyzedDSH bundle plugin: chat-image bridge + read_image deny + conversational image_recognize for text-only main models | 纯文本主模型识图桥接与识图工具CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals3 starsdsh-image-transcription-pluginkutcr/dsh-image-transcription-pluginCatalog AnalyzedDeepSeek Harness Cordis plugins for durable image transcription and on-demand historical image recall.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals4 starsdsh-image-understandingrison114514/dsh-image-understandingCatalog Analyzeddeepseek-harness 原生Plugin：让纯文本模型(如 DeepSeek)经 agent/pre-step 劫持 + resolveModelInfo 包装自动识别上传图片(qwen-vl)CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals2 starsdsh-latex-ocrYunnalab/dsh-latex-ocrCatalog AnalyzedDSH plugin from Yunnalab/dsh-latex-ocrCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 starsdsh-ocrdsh-ocrCatalog AnalyzedOCR tools for dsh agents - name reserved; first release in development.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifact0.0.1Evidence updated2026-09-26Public signals169 downloadsdsh-ocr-bridgedsh-ocr-bridgeCatalog AnalyzedPaste images into DeepSeek Harness chat and have them read by a free local backend (macOS Vision / Tesseract) before the text-only DeepSeek model answersCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.1Evidence updated2026-09-25Public signals567 downloadsdsh-ocr-localdsh-ocr-localCatalog AnalyzedLocal OCR fallback for text-only routes: when the session model declares it cannot accept images, the attached image is cached locally and its path injected so the model can call ocr_image — PP-OCRv5 + ONNX Runtime on CPU, no API key, images never leave the machine. Silent when the model can see images.CompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.4.3Evidence updated2026-09-20Public signals5 stars · 626 downloadsdsh-omni-visionRenji004/dsh-omni-visionCatalog AnalyzedLocal eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in the Web GUI, eyes_paste captures pasted images, eyes_ocr reads text via the built-in Windows OCR (offline), and eyes_analyze inspects pixels as structured data — no vision model required.CompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals0 stars
Categories are public semantic index facts, not a final recommendation. Compatibility, permissions, and source evidence remain separate.