Show HN: Open-source PDF tools with local OCR and AI search in the browser

Category: other

Tags: pdf-tools, privacy-first, ocr

Score: 6.8/10 (Innovation: 6, Technical: 7, Documentation: 7, Utility: 7)

PDFClear is an open-source, privacy-first PDF toolkit that runs entirely in the browser, offering local OCR, AI summarization, and semantic search without uploading files. It combines a comprehensive set of PDF operations with cutting-edge browser-based AI, making it both practical and privacy-focused. Its use of Transformers.js and Tesseract.js for local processing is an innovative approach for a web-based PDF tool.

Target audience: backend devs, frontend devs, devops

Repository: https://github.com/aliansari22/pdfclear · TypeScript · Apache-2.0

View on Hacker News