Crawl4AI simplifies asynchronous web crawling and data extraction, making it accessible for large language models (LLMs) and AI applications.
Looking for the synchronous version? Check out README.sync.md. You can also access the previous version in the branch V0.2.76.
β¨ Visit our Documentation Website
Crawl4AI offers flexible installation options to suit various use cases. You can install it as a Python package or use Docker.
Choose the installation option that best fits your needs:
For basic web crawling and scraping tasks:
pip install crawl4ai
By default, this will install the asynchronous version of Crawl4AI, using Playwright for web crawling.
π Note: When you install Crawl4AI, the setup script should automatically install and set up Playwright. However, if you encounter any Playwright-related errors, you can manually install it using one of these methods:
playwright install For more information click here.
Journalists use OSINT to verify public information before publishing. In 2026, misinformation, AI-generated images, fake…
DockerΒ is an open-source platform that lets you package and run applications inside containers. Each container…
PostgreSQL (often called Postgres) is an open-source relational database system. It supports advanced features like JSON…
Xrdp is an open-source server that lets you connect to your Ubuntu machine from another computer…
Apache Tomcat is an open-source web server and Java servlet container. It is one of the…
Keeping your Ubuntu system updated is one of the best ways to protect it. Security…