Firecrawl
A web-data API for search, scraping, document parsing, and interaction. It supplies agent-ready content and structured extraction, with both public code and a hosted service.
Utility: Browser automation; kind: infrastructure.
Stars: 197k+; Starred in September: 12k+.
Metrics updated: 31 Oct 2026. Profile reviewed: 31 Oct 2026.
Utilities
- Convert web pages into Markdown or structured JSON for an agent.
- Search and retrieve source material for retrieval pipelines.
Who it is for
- Developers building agents that need web or document context.
Requirements
- Use a hosted API key or follow the self-hosting documentation.
- Configure the client SDK and any required deployment services.
Limitations
- The hosted service includes capabilities beyond the open-source deployment.
- Extraction can omit content, and website terms still constrain collection.
Cost and privacy notes
- Hosted API credits, model-assisted operations, and self-hosted infrastructure have different costs.
- Requests and retrieved documents pass through whichever hosted or self-hosted components you configure.
Illustrative example (untested)
Illustrative, not tested: scrape public documentation into Markdown and check the result before indexing it.
License
AGPL-3.0 for repository code; hosted service terms and additional components require separate review.