firecrawl

firecrawl/firecrawl

The API to search, scrape, and interact with the web at scale.

147k
Stars
8.5k
Forks
387
Open issues
390
Watchers
TypeScript AGPL-3.0Last pushed Jul 7, 2026

Overview

Firecrawl is an open-source and hosted service that offers a web context API for searching, scraping, and interacting with the web. It provides reliable data extraction services, supports LLM-ready output formats like clean markdown and structured JSON, ensuring high-quality interactions with web content.

Categories

Tags

Similar tools

Install

npm install firecrawl

README


🔥 Firecrawl

The API to search, scrape, and interact with the web at scale. 🔥 The web context API to find sources, extract content, and turn it into clean Markdown or structured data your agents can ship with. Open source and available as a hosted service.

Pst. Hey, you, join our stargazers :)

GitHub stars

Why Firecrawl?

  • Industry-leading reliability: Covers 96% of the web, including JS-heavy pages — no proxy headaches, just clean data (see benchmarks)
  • Blazingly fast: P95 latency of 3.4s across millions of pages, built for real-time agents and dynamic apps
  • LLM-ready output: Clean markdown, structured JSON, screenshots, and more — spend fewer tokens, build better AI apps
  • We handle the hard stuff: Rotating proxies, orchestration, rate limits, JS-blocked content, and more — zero configuration
  • Agent ready: Connect Firecrawl to any AI agent or MCP client with a single command
  • Media parsing: Parse and extract content from web-hosted PDFs, DOCX, and more
  • Actions: Click, scroll, write, wait, and press before extracting content
  • Open source: Developed transparently and collaboratively — join our community

Feature Overview

Core Endpoints

FeatureDescription
SearchSearch the web and get full page content from results
ScrapeConvert any URL to markdown, HTML, screenshots, or structured JSON
InteractScrape a page, then interact with it using AI prompts or code

More

FeatureDescription
AgentAutomated data gathering, just describe what you need
CrawlScrape all URLs of a website with a single request
MapDiscover all URLs on a website instantly
Batch ScrapeScrape thousands of URLs asynchronously

Quick Start

Sign up at firecrawl.dev to get your API key. Try the playground to test it out.

Search

Search the web and get full content from results.

from firecrawl import Firecrawl

a