Firecrawl
Open-source web data API that lets AI agents search, scrape, crawl and interact with websites as clean markdown or JSON
Firecrawl is an open-source web data API that lets AI agents and developers search, scrape, crawl and interact with websites. It returns clean, LLM-ready markdown, JSON or screenshots, and can click, type and scroll through pages after scraping them.
Key features:
- Searches the web and returns the full content of results.
- Scrapes pages into markdown, JSON or screenshots with JavaScript rendering and smart waits.
- Maps and crawls entire sites.
- Interacts with pages using prompts or code: click, scroll, type and press.
- Parses PDFs, DOCX and other media.
- Connects to AI agents through an MCP server, CLI and skills.
Firecrawl offers SDKs for Python and Node.js, a cURL interface and a CLI, and the core project is open source and can be self-hosted. The hosted free plan gives 1,000 credits a month with no card. Hobby is $19/month, Standard $99/month, Growth $399/month and Scale $749/month, about 16-20% less billed annually; Enterprise adds zero data retention and SSO.