BlinkID Core SDK
Read Indonesian NPWP cards on the user's device. Built on ktp-kit's pipeline.
Portable native RapidOCR NCNN, with Chinese/English models; no Python
Fork of Dennnisk's original ocr-space-api with added support for PDF uploading. Provides an easy way to send images to the ocr.space API and get the OCR Result
Local OCR for DeepSeek Harness: read text out of images with Apple Vision on macOS — no network, no API key, nothing to install. Falls back to tesseract elsewhere.
Extract text from images and PDFs in DeepSeek Harness: read a born-digital text layer, or OCR a scan with any engine you configure.
In-browser document conversion: DOCX, HTML, XLSX, PPTX, EPUB, Markdown, … and the text layer of PDFs → Markdown / docling JSON / DocLang, fully client-side (docling.rs compiled to WebAssembly)
An Appium plugin that uses OCR (Optical Character Recognition) to find and click text elements on mobile device screens with AI-powered screen analysis
Scan images on CLI
Mobile web app that captures photos and extracts text using a local llama.cpp LLM server
Fast PDF classification, text extraction, and image extraction. Native Rust performance via napi-rs.
Portable native RapidOCR NCNN, with Chinese/English models; no Python
React Native module for BlinkCard, SDK for scanning and OCR of credit or payment cards.
Simple to use module to recognize texts in images by an image url
A Vue.js project
The_powerful_Optical_Character_Recognition__OCR_APIs_let_you_convert_scanned_images_of_pages_into_recognized_text_
OCR.space plugin for Corsair
Composer + button: OCR the clipboard image locally (macOS Vision) and insert the text into the DSH input box.
Node PDF is a set of tools that takes in PDF files and converts them to usable formats for data processing. The library supports both extracting text from searchable pdf files as well as performing OCR on pdfs which are just scanned images of text
Platform binary for open-code-review (linux arm64)
发票OCR识别与导入弹窗组件
Document classification using tesseract.js and string-similarity-js.
SDK JavaScript/TypeScript officiel pour l'API OCR Facture France - Extraction automatique de données de factures via OCR
OCR and PDF extraction adapter for the @quatrain/ingestion namespace
Native windows-x64 runtime for @arcships/light-ocr
TypeScript OCR for Node.js, following the RapidOCR pipeline and ONNX models.
Portable native RapidOCR NCNN, with Chinese/English models; no Python
Lazy, self-hosted Tesseract OCR provider for @pdfextract/core in browsers and Node.js. No CDN or implicit model downloads.
catbus 的验证码 OCR 模型:ddddocr 1.6.1 的检测模型、识别模型与字符集
A Vue.js project
🔍 Find files that contain some text with OCR
- `OcrLlmSDK` 是一个基于轮询机制的 OCR + LLM 异步任务管理 SDK,提供任务创建、结果获取、状态监听等功能,支持 **图片 URL**、**Base64**、**二进制文件** 方式发起任务,并可自动轮询更新任务状态与结果。
A React Native library for scanning tags
Sogni SDK - AI image, video & audio generation plus LLM chat with vision via the Sogni Supernet (Stable Diffusion, Flux, WAN, LTX-2, Seedance, HappyHorse, Qwen VLM)
Add a custom document scanner to your web apps by using and customizing our proven imaging technology. The Document Scanner SDK is the same software that we use at the core of Genius Scan: it's tried and trusted every day by millions of people on iOS and
Native macos-arm64 runtime for @arcships/light-ocr
Node.js module for communicating with the Veryfi OCR API
Advanced OCR text recognition for React Native with Vision API (iOS) and ML Kit (Android). Supports multi-language recognition, PDF files, and both old and new React Native architectures.
Anyline Web SDK
Open-source retrieval for agentic RAG: document search with exact citations on your laptop or servers, with OCR, CLI, MCP, and TypeScript.
Pure Javascript Multilingual OCR
Portable native RapidOCR NCNN, with Chinese/English models; no Python
Native Node.js bindings for the Tesseract OCR project.