Various tools for OCR
Framework-agnostic desktop computer-use tool for AI agents: screenshot, mouse, keyboard, OCR, overlay
Optional OCR runtime package for docparser-core — adaptive OCR pipelines, local Tesseract engines, and image preprocessing
Allow to access ocr.space API to send images and get the OCR Result (get the image text)
Anyline Web SDK
paddleocr models run on onnx
On-device OCR module for Expo and React Native using ML Kit (Android) and Vision (iOS)
OCR via system provided API
High-performance client-side OCR with ONNX Runtime, RapidOCR and PPU PaddleOCR integration. 100+ language support. Process text from images entirely in the browser with state-of-the-art accuracy and complete privacy.
Link → clean text → summary.
The official TypeScript library for the Llama Cloud API
n8n community node for Deep-OCR document processing API
Native PDF text extraction for React Native and Expo. Extract text content from PDF files using platform-native APIs (PDFKit on iOS, PDFBox on Android). Works with Expo development builds.
Fork of tesseract.js used for scribe.js. Pure Javascript Multilingual OCR
Webcomponent ocr following open-wc recommendations
Native Node.js bindings for the Tesseract OCR project.
⚠️ DEPRECATED — migrated to pi-ocr
Utilitários de ancoragem OCR para extração de biomarcadores de PDFs de resultados laboratoriais
## **Content:**
n8n community node for PDF processing - convert PDF to images, extract text and run OCR
Fast PDF classification and text extraction. Detect text-based vs scanned PDFs, extract text by region with quality checks. Native Rust performance via napi-rs.
A React Native library for scanning tags
Fast, lightweight PDF and document parsing with spatial text extraction
Bundled Tesseract OCR runtime for Discord Waifus on Windows x64.