#77th of 29 in Data and scraping for AI
Firecrawl
Web API that turns sites and searches into markdown or JSON for LLMs
- Stars
- 194.8k
- License
- AGPL-3.0
- Last commit
- Oct 2026
- Last release
- Jun 2026
- Language
- TypeScript
97,089 on 27 Mar 2026194,783 on 23 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Firecrawl is hiring: 33 open roles
Overview
Firecrawl exposes REST endpoints to search the web, scrape a URL, crawl a site, map its URLs, batch-scrape, parse documents (PDF, DOCX) and run page actions such as click and scroll. Output is markdown, HTML, screenshots or schema-based JSON. SDKs cover Python, Node.js, Go, Java, Elixir, Rust and Ruby, plus a CLI and an MCP server. The README examples use the hosted API with a key; self-hosting details are not in the excerpt.
Who it is for: Developers feeding web content to LLM apps and agents
Ranked among open-source alternatives to Apify (#6 of 10).
Strengths
- Endpoints for search, scrape, crawl, map, batch scrape and document parsing
- Official SDKs for seven languages, plus a CLI and MCP server
- Outputs markdown, HTML, screenshots or schema-based structured JSON
- Page actions and an interact endpoint for JS-heavy pages
Weaknesses
- README examples target the hosted API and require an API key
- AGPL-3.0 license restricts use in closed-source network services
- Agent endpoint runs the spark-2 model; self-hosted availability is unknown
- Self-hosting requirements (RAM, ports, proxies) not stated in the README excerpt
What it needs
- Compose
- Needs Firecrawl API key (hosted service)
- Models: spark-2
Quick answers
Is Firecrawl open source?
Yes. Its code is on GitHub under the AGPL-3.0 license.
Can you run Firecrawl with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Head to head
Also in Data and scraping for AI
See all 29| Rank | Project | Score |
|---|---|---|
| 1 | mineruDocument parser that converts PDFs, images and Office files to Markdown and JSON | 94 out of 100 |
| 2 | doclingPython library and CLI that converts PDFs, Office files and more into structured text | 91 out of 100 |
| 3 | markitdownPython library and CLI that converts office files, PDFs and audio to Markdown | 86 out of 100 |
| #4 | Crawl4AIAsync Python web crawler that outputs LLM-ready Markdown and structured JSON | 84 out of 100 |
| #5 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 84 out of 100 |