crawl4ai

v0.9.5

unclecode/crawl4ai

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.

Compare View on GitHub

Maintenance: Active101 commits in 3 months · bus factor 1
License: Apache-2.0Permissive · OSI-approved
Security: 25 advisories5 critical, 12 high, 8 medium
Supported versions: No scheduleendoflife.date does not track this project

87.4k stars · 9.1k forks · 349 open issues · last release 1 month ago · data checked 43 minutes ago

Overview Tour Releases Docker images Security Logos

Breaking changes

What to check before upgrading, taken from the notes of the last 23 releases.

v0.7.5Oct 21, 2025
- ⚠️ Breaking Changes
v0.7.0Jul 12, 2025
Breaking Changes
- link_extractor renamed to link_preview (better reflects functionality)
- Minimum Python version now 3.9
- CrawlerConfig split into CrawlerRunConfig and BrowserConfig
Migration Guide
v0.6.3May 12, 2025
- crawler: remove automatic page closure in take_screenshot and take_screenshot_naive, preventing premature teardown; callers now must explicitly close pages (BREAKING CHANGE) (a3e9ef9)
v0.5.0.post1Mar 4, 2025
Breaking Changes
This release contains several breaking changes. Please review the full release notes for migration guidance.
For complete details, visit: https://docs.crawl4ai.com/blog/releases/0.5.0/

Release history

All releases on GitHub

Atom feed/feed/unclecode/crawl4ai

Badge

[![version](/badge/unclecode/crawl4ai)](/p/unclecode/crawl4ai)

Release v0.9.5

🎉 Crawl4AI v0.9.5 Released!

📦 Installation

PyPI:

pip install crawl4ai==0.9.5

Docker:

docker pull unclecode/crawl4ai:0.9.5
docker pull unclecode/crawl4ai:latest

Note: Docker images are being built and will be available shortly.

Check the Docker Release workflow for build status.

📝 What's Changed

See CHANGELOG.md for details.

Full release notes Compare with previous