FrankieOne OneSDK
Framework-agnostic desktop computer-use tool for AI agents: screenshot, mouse, keyboard, OCR, overlay
PDF to Markdown and DOCX conversion powered by Mistral OCR.
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
High-quality OCR and text extraction for images and PDFs.
paddleocr models run on onnx
A Node.js wrapper for the Python EasyOCR library
The Adobe PDF Services Node.js SDK provides APIs for creating, combining, exporting and manipulating PDFs.
n8n community node for Deep-OCR document processing API
VisionCamera Frame Processor Plugin to provide OCR support
n8n community nodes for Nextcloud — file management (list, upload, download, share), spreadsheet operations equivalent to Microsoft 365 Excel (including named table support), DOCX/ODT template rendering, and PDF form field read/write (AcroForm)
Repeato OCR for Node.js main threads and Electron renderers, based on PaddleOCR and ONNX Runtime
A robust, strictly-typed Node.js and Browser library for parsing office files (.docx, .pptx, .xlsx, .odt, .odp, .ods, .pdf, .rtf, .csv, .md, .html) and generating high-fidelity outputs in Markdown, HTML, CSV, RTF, and RAG-focused chunks.
Read text and parse tables from PDF files. Supports tabular data with automatic column detection, and rule-based parsing.
A n8n module that exposes Tesseract.js, an OCR library that can detect text on images
Swedish invoice no generator
Local Discord waifu orchestrator backend, web UI, and CLI.
A WebdriverIO service that is using Tesseract OCR for Appium Native App tests.
Bundled Tesseract OCR runtime for Discord Waifus on macOS arm64.
6 MB Tesseract 4.1 (with English training data) to fit inside AWS Lambda
Bundled Tesseract OCR runtime for Discord Waifus on Linux x64 glibc.
Bundled Tesseract OCR runtime for Discord Waifus on macOS x64.
Math-OCR Component Library — React 19 · HeroUI 3 · Tailwind 4 · Storybook 10
Pi extension: Zero-setup multi-backend OCR — MinerU (free cloud), Ollama (local GPU, LaTeX formulas), Pix2Text (local Python). Extract text, formulas, and tables from images and PDFs. Default: zero config, works out of the box.