Crawl4AI (v0.9.5, October 2026) is a Python library, CLI and Docker server that drives a headless browser to crawl sites into Markdown with content filters and citations, and extracts JSON with CSS/XPath schemas (no LLM) or any LiteLLM provider, including Ollama. It has proxy, session and stealth options. Licence is Apache-2.0 with an added attribution requirement in the LICENSE file. A paid Crawl4AI Cloud adds web search and managed bot handling. Users must respect site terms and robots.txt.
Cite this pageRepoQuarry. “Crawl4AI.” Checked 16 Oct 2026. https://repoquarry.dev/projects/crawl4ai
How much of Firecrawl Cloud does it replace?
3 of 4 jobs. You run the browsers and supply any proxies yourself; no built-in web search in the open-source version.
Partial:Crawl a site to MarkdownPartial replacement
Partial:Scrape pages (JS-heavy and bot-protected)Partial replacement
Partial:Structured data extractionPartial replacement
No:Web search with page contentNot covered
For web search with page content, see other Firecrawl Cloud alternatives. You may also need to build an interface, an API server and hosting yourself.
Facts, with sources
Every answer links to where we found it. We read the documentation; we did not install it.
Runs on my machine?Confirmed:Yes, in your Python process or a Docker server on your machineRun the open-source web crawler and scraper yourself, free forever, or use it hosted with one keygithub.com · crawl4ai#which-one ↗1d ago
Code licencePartial:Apache-2.0 plus an added attribution requirementAll distributions, publications, or public uses of this software, or derivative works based on this software, must include the following attributiongithub.com · LICENSE ↗1d ago
Model weights licenceConfirmed:No separate model weights; LLM extraction uses the provider you connectgithub.com · crawl4ai#readme ↗1d ago
Commercial usePartial:Yes, with the attribution required by the LICENSE fileThis attribution must be displayed in a prominent and easily accessible locationgithub.com · LICENSE ↗1d ago
Paid services needed?Confirmed:None required; LLM extraction optional (local Ollama or paid APIs), Crawl4AI Cloud optionalno keys needed, CLI and Docker, or the hosted cloudgithub.com · crawl4ai#which-one ↗1d ago
Operating systemsPartial:Official installation guide includes Ubuntu-specific Playwright dependency instructions; Windows and macOS support are not confirmed in the reviewed installation pagesdocs.crawl4ai.com · installation ↗today
Setup effortConfirmed:Easy, pip install crawl4ai then crawl4ai-setup to install the browserpip install -U crawl4aigithub.com · crawl4ai#readme ↗1d ago
Your choice on cookies
We use essential storage to keep the site secure and remember this choice. With your permission we'd also count visits to see which pages help people, and remember your filters. We never use advertising or cross-site tracking cookies, and sponsors never get your data. Cookie policy