Explore Projects
Discover 30 open source projects
Showing 1-20 of 30 projects
PaddlePaddle/PaddleOCR
PaddleOCR converts documents/images to structured data for AI apps
opendatalab/MinerU
Converts complex documents into LLM-ready formats for agentic workflows
YaoFANGUK/video-subtitle-extractor
A Python tool for extracting hard-coded subtitles from videos and generating SRT files using deep learning-based OCR.
MetrolistGroup/Metrolist
A YouTube Music client for Android with a modern Material Design UI and features like NewPipe integration.
peazip/PeaZip
A free and open-source file archiver and compression tool with support for various archive formats.
microsoft/rushstack
A monorepo for a set of tools developed by the Rush Stack community for TypeScript-based projects.
adbar/trafilatura
Gathers text and metadata from the web using crawling, scraping, and extraction techniques.
GeneralNewsExtractor/GeneralNewsExtractor
Python-based AI news extractor beta version
miso-belica/sumy
A Python module for automatic summarization of text documents and HTML pages.
luigifreda/pyslam
Python/C++ Visual SLAM pipeline for 3D reconstruction
Purfview/whisper-standalone-win
Standalone Windows executables for Whisper speech-to-text & diarization without Python setup.
drewnoakes/metadata-extractor
A Java library for extracting metadata from various media file formats, including images, videos, and audio.
nelenkov/android-backup-extractor
An Android backup extractor tool written in Java for developers working with Android devices.
fhamborg/news-please
news-please is an integrated web crawler and information extractor for news that works out of the box.
UglyToad/PdfPig
A C# library for reading and extracting text and other content from PDF files, ported from the Java PDFBox library.
Achno/gowall
A go-based tool to process images with features like color palette extraction, OCR, upscaling, and more.
extractus/article-extractor
A Node.js library for extracting the main article content from a given URL using the Readability algorithm.
TeamNewPipe/NewPipeExtractor
A Java library for extracting data from various streaming platforms like YouTube, SoundCloud, and Bandcamp.
echohive42/AI-reads-books-page-by-page
An AI-powered tool that extracts knowledge and generates summaries from PDF books, page by page.
GravityLabs/goose
A Scala library for extracting HTML content and articles from web pages.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.