Open Source
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace.

Scrapling is an adaptive web scraping framework by D4Vinci that handles everything from single HTTP requests to full-scale crawls. It uses intelligent similarity algorithms to track elements even when website structures change, eliminating scraper breakage. It features multiple fetchers including StealthyFetcher with Cloudflare bypass, DynamicFetcher with Playwright automation, and a Scrapy-like Spider API with concurrency control. A built-in MCP server enables AI-assisted scraping with Claude and other tools, minimizing token usage by extracting targeted content before passing to AI.
langflow-ai
Open-source visual platform for building AI agents and workflows with 145k+ stars, drag-and-drop interface, and full Python customization
microsoft
Lightweight Python utility from Microsoft that converts virtually any file format—PDFs, Word docs, PowerPoints, images, audio, and web pages—into clean, token-efficient Markdown for LLM integration.
firecrawl
Open-source Web Data API for AI that converts websites into LLM-ready markdown, structured JSON, and screenshots with 96% web coverage.
microsoft
Microsoft's lightweight Python utility converting PDFs, Office docs, images, audio, and more into clean Markdown optimized for LLM pipelines, with MCP server integration