Open SourceScraping60k

Firecrawl

Turn any website into clean LLM-ready markdown or structured data.

Firecrawl is a service and open-source toolkit that crawls websites and converts pages into clean, LLM-ready formats such as markdown and structured data, handling JavaScript rendering and proxies. It exposes scrape, crawl, and extract endpoints with an API and SDKs. It is notable for turning entire sites into content optimized for RAG and LLM ingestion.

View repo

Repository

firecrawl/firecrawl

Language

TypeScript

What you'd build with it

Converting websites into clean markdown for RAG and LLM context
Crawling all pages of a site through a single API call
Extracting structured data from pages with schema-based extraction

Repository

Language

What you'd build with it

Tags