Verified project record

firecrawl/firecrawl

Firecrawl is a hosted web scraping, crawling, and search API built for AI applications. It converts web pages into Markdown, structured JSON, screenshots, and HTML while handling rotating proxies and rate limits.

Project overview

Project type: AI Agent · AI Search · Data Processing
Use cases: Search & Research · Automation
Deployment: Refer to project documentation
License: AGPL-3.0

Best for

Developers who need a hosted API to extract web content into Markdown or structured JSON without managing rotating proxies or rate limits.
AI engineers building applications that require searching, crawling, or interacting with web pages to gather data.

Key capabilities

Searches the web and returns full page content from the results.
Converts any URL into Markdown, HTML, screenshots, or structured JSON.
Scrapes a page, then uses AI prompts or code to click, scroll, write, wait, and press before extracting content.
Accepts a description of needed data so the agent can autonomously search, navigate, and retrieve it without requiring URLs.
Scrapes all URLs of a website with a single request.
Discovers all URLs on a website.
Scrapes thousands of URLs asynchronously.
Parses and extracts content from web-hosted PDFs, DOCX, and similar files.

Limitations and risks

Requires a Firecrawl API key to operate.
End users are solely responsible for respecting the policies of scraped websites.

Getting started

Sign up at firecrawl.dev to obtain an API key, install the Python or Node.js SDK via pip or npm, and run a scrape or search command.

Evidence and sources

GitHub project description: The API to search, scrape, and interact with the web at scale. 🔥
README: The web context API to find sources, extract content, and turn it into clean Markdown or structured data your agents can ship with.
README: Firecrawl helps AI systems search, scrape, and interact with the web.
README: We handle the hard stuff: Rotating proxies, orchestration, rate limits, JS-blocked content, and more — zero configuration
README: Search the web and get full page content from results

Reviewed at: 2026-07-16T08:12:17Z