AI Agent Skills

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

📚 Biblioteca de livros essenciais da área da programação. (Confira o meu novo projeto `SendScriptWhatsapp`)

PDF craft can convert PDF files into various other formats. This project will focus on processing PDF files of scanned books.

Small python-gtk application, which helps the user to merge or split PDF documents and rotate, crop and rearrange their pages using an interactive and intuitive graphica…

Rust 程序设计语言（2024 edition 施工完毕）

Advanced real-time screen translator for games, hardcoded subtitles in videos, static text and etc.

超轻量级中文ocr，支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

Ui.Vision Open-Source RPA Software with Computer Vision, OCR, Anthropic Computer Use/LLM. Selenium IDE import/export.

KCC (a.k.a. Kindle Comic Converter) is a comic and manga converter for ebook readers.

qpdf: A content-preserving PDF document transformer

Bartosz Milewski's 'Category Theory for Programmers' unofficial PDF and LaTeX source

A Canvas/SVG-based rich text editor

Open-source office suite pack that comprises all the tools you need to work with documents, spreadsheets, presentations, PDFs, and PDF forms on Windows, Linux, and macOS

A machine learning software for extracting information from scholarly documents

OCR model that handles complex tables, forms, handwriting with full layout.