Is crawl4ai open source?
Yes, in the sense that crawl4ai publishes source under Apache-2.0. This catalog files that grant as permissive. This is not legal advice.
GitHub checked 17 Nov 2026
Official Crawl4AI Cloud: a hosted web scraping, extraction, and search API for AI agents. Free API key, 1,000 credits a month, no card. Fully open source: this repo is the Apache-2.0 crawler that powers it, and you can self-host it.
crawl4ai ranks 20 of 108 AI Agents tools in this catalog by GitHub stars, with 87,471 stars. The category average is 59,811. crawl4ai sits 27,660 stars above that average.
Primary language on file: Python. Forks: 9,125. Open issues: 347 (0.004 per star). Push history: crawl4ai was last pushed on 17 November 2026 (0 days ago).
crawl4ai is listed as Apache-2.0, which this catalog treats as a permissive grant. A company can usually ship it inside a commercial product and keep its own application code private, provided it keeps the copyright notice. The pricing label in this catalog is open source. This is not legal advice.
This catalog marks crawl4ai as self-hostable: the source is public and a license or an explicit self-host signal is on file. Confirm the deployment docs before you plan a migration. It is filed under AI Agents.
Yes, in the sense that crawl4ai publishes source under Apache-2.0. This catalog files that grant as permissive. This is not legal advice.
This catalog marks crawl4ai as self-hostable: the source is public and a license or an explicit self-host signal is on file. Confirm the deployment docs before you plan a migration.
crawl4ai has 87,471 GitHub stars and 9,125 forks in this catalog, ranked 20 of 108 in AI Agents.
In this catalog the closest AI Agents alternatives by stars are ECC, deepseek-harness, hermes-agent, firecrawl, ponytail.