firecrawl
🔥 Search, scrape, and clean the web for AI agents.
TL;DR · 30-second scan
firecrawl (TypeScript) — 🔥 Search, scrape, and clean the web for AI agents.
You're building a RAG agent, a competitive-intel tool, or any system that ingests web content as training/search data.
AI & ML
The 2026 default for LLM-grade scraping. Fires Playwright behind the scenes, returns clean markdown ready to feed into RAG. Self-host for free or use the hosted tier — both expose the same API. The sweet spot when you want a scraper that knows what a content-page looks like vs a nav-page, and skips the cruft automatically.
You're building a RAG agent, a competitive-intel tool, or any system that ingests web content as training/search data.
You're scraping structured APIs (JSON endpoints) — overkill. Use plain fetch + Zod.
Add this badge to your README to show your project is curated on StackPicks. Free, lightweight (180×28 SVG), and gives your visitors a one-click way to see honest take + alternatives.
[](https://stackpicks.dev/repo/firecrawl-firecrawl)
<a href="https://stackpicks.dev/repo/firecrawl-firecrawl"><img src="https://stackpicks.dev/api/badge/firecrawl-firecrawl" alt="Featured on StackPicks" width="180" height="28" /></a>
Are you the maintainer of firecrawl/firecrawl? Add the badge and we'll feature your project in the next weekly newsletter (~2,000 builders).