firecrawl

Overview

Firecrawl provides a powerful API and CLI to search, scrape, and interact with the web. It turns any URL into clean Markdown or structured JSON, ideal for LLM applications and AI agents. Supports crawling, batch scraping, and interactive page actions.

README Preview

\n  \n  \n\n\n\n  \n    \n  \n  \n    \n  \n  \n    \n  \n  \n    \n  \n\n\n\n  \n    \n      \n    \n    \n      \n    \n    \n      \n    \n  \n\n\n---\n\n# **🔥 Firecrawl**\n\n**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](https://firecrawl.dev/?ref=github).\n\n_Pst. Hey, you, join our stargazers :)_\n\n\n  \n\n\n---\n\n## Why Firecrawl?\n\n- **Industry-leading reliability**: Covers 96% of the web, including JS-heavy pages — no proxy headaches, just clean data ([see benchmarks](https://www.firecrawl.dev/blog/the-worlds-best-web-data-api-v25))\n- **Blazingly fast**: P95 latency of 3.4s across millions of pages, built for real-time agents and dynamic apps\n- **LLM-ready output**: Clean markdown, structured JSON, screenshots, and more — spend fewer tokens, build better AI apps\n- **We handle the hard stuff**: Rotating proxies, orchestration, rate limits, JS-blocked content, and more — zero configuration\n- **Agent ready**: Connect Firecrawl to any AI agent or MCP client with a single command\n- **Media parsing**: Parse and extract content from web-hosted PDFs, DOCX, and more\n- **Actions**: Click, scroll, write, wait, and press before extracting content\n- **Open source**: Developed transparently and collaboratively — [join our community](https://github.com/firecrawl/firecrawl)\n\n---\n\n## Feature Overview\n\n**Core Endpoints**\n\n| Feature | Description |\n|---------|-------------|\n| [**Search**](#search) | Search the web and get full page content from results |\n| [**Scrape**](#scrape) | Convert any URL to markdown, HTML, screenshots, or structured JSON |\n| [**Interact**](#interact) | Scrape a page, then interact with it using AI prompts or code |\n\n**More**\n\n| Feature | Description |\n|---------|-------------|\n| [**Agent**](#agent) | Automated data gatherin