Explore Projects
Discover 385 open source projects
Showing 1-20 of 385 projects
firecrawl/firecrawl
Convert websites into LLM-ready data with API for scraping, crawling, and structured data extraction
opendatalab/MinerU
Converts complex documents into LLM-ready formats for agentic workflows
naptha/tesseract.js
JavaScript OCR library for image text extraction
SheetJS/sheetjs
SheetJS Spreadsheet Data Toolkit for data extraction and spreadsheet generation.
google/langextract
Extracts structured info from text using LLMs with source grounding
asgeirtj/system_prompts_leaks
Collection of system prompts from popular chatbots for developers
D4Vinci/Scrapling
Powerful, flexible Python library for effortless web scraping with AI-powered features.
ScrapeGraphAI/Scrapegraph-ai
AI-powered web scraping library for extracting data from websites and documents
apify/crawlee
Web scraping and browser automation library for Node.js
gentilkiwi/mimikatz
Extracts credentials and performs security testing on Windows systems
gildas-lormeau/SingleFile
Saves web pages as single HTML files
Evil0ctal/Douyin_TikTok_Download_API
A high-performance async web scraping tool for extracting data from Douyin, TikTok, Bilibili and more.
tidwall/gjson
A fast and efficient JSON parser for Go that allows developers to quickly extract values from JSON data.
getmaxun/maxun
Turn websites into clean data pipelines & structured APIs in minutes with a low-code web scraping tool.
Perfare/AssetStudio
AssetStudio is a tool for exploring, extracting and exporting Unity assets and asset bundles.
codelucas/newspaper
A Python library for extracting news articles, full-text, and metadata from websites.
coderamp-labs/gitingest
A Python tool that generates a prompt-friendly extract of a GitHub codebase by replacing 'hub' with 'ingest' in any GitHub URL.
interagent/http-api-design
A guide for designing HTTP APIs, extracted from work on the Heroku Platform API.
ReFirmLabs/binwalk
An open-source firmware analysis tool written in Rust that can be used to extract, analyze, and identify embedded firmware components.
moonD4rk/HackBrowserData
A cross-platform tool to extract and decrypt browser data, supporting multiple data types.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.