Crawl4AI is a free, open source data extraction & web scraping project written in Python and released under Apache-2.0. It has 83,747 GitHub stars, 8,660 forks and 188 open issues, and was last pushed 40 hours ago. On this registry it ranks #1 of 45 tracked projects in Data Extraction & Web Scraping, with 5 head-to-head comparisons available. It gained 1,207 stars over the last 6 tracked days.

What is Crawl4AI?

What it is

Crawl4AI is an open-source web crawler and scraper designed to prepare website content for large language model (LLM) workflows. It lives in the Python ecosystem and targets data extraction for RAG, agents, and AI pipelines. Unlike many tools that require API keys or paid subscriptions, Crawl4AI provides direct, self-hosted access to web content with output structured specifically for LLM consumption.

It solves the problem of unreliable, expensive, or non-LLM-optimized web data ingestion. Existing solutions often deliver HTML, JSON, or unstructured text that demands heavy preprocessing before use in LLM pipelines. Crawl4AI converts pages into clean, semantic Markdown—including headings, tables, code blocks, and citation hints—reducing downstream processing overhead and improving LLM fidelity.

Key capabilities

  • Converts web pages to LLM-ready Markdown with semantic structure (headings, lists, tables, code blocks)
  • Supports async browser-based crawling using Playwright for dynamic content rendering
  • Provides domain-scoped deep crawling with crash recovery via resume_state and on_state_change callbacks
  • Includes a Docker API server with optional authentication, loopback binding, and trust-boundary request handling
  • Offers PDF processing with security hardening (no arbitrary file write, SSRF, or DoS in PDF path)
  • Features prefetch=True mode for 5–10× faster URL discovery in large crawls
  • Ships with DomainMapper for URL-based routing and filtering during crawling

Who uses it and how

  • AI engineers integrate it into RAG pipelines to ingest and preprocess internal or public documentation as Markdown for embedding
  • Data scientists run self-hosted crawls on cron or Kubernetes to populate training or fine-tuning datasets
  • Developers deploy the Docker API server as a local service to power agent tooling, with domain-limited crawling and auth enabled

Getting started

Install via pip install crawl4ai, run locally with python -m crawl4ai, or deploy the Docker image unclecode/crawl4ai with optional ENABLE_GPU=true and CRAWL4AI_API_TOKEN for secure API access. A hosted cloud API is in closed beta.

When to use it — and when not to

Use Crawl4AI when you need self-hosted, LLM-optimized extraction without recurring API costs or vendor lock-in. It is not ideal when you require real-time, low-latency scraping (Playwright-based crawling adds overhead), or when you lack infrastructure to manage Playwright browsers, Docker, or storage for large crawl outputs. The Docker server requires explicit token setup for external access; by default it binds loopback only.

project readme (upstream, from github) — read inline

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper.

unclecode%2Fcrawl4ai | Trendshift

GitHub Stars GitHub Forks

PyPI version Python Version Downloads GitHub Sponsors


🚀 Crawl4AI Cloud API — Closed Beta (Launching Soon)

Reliable, large-scale web extraction, now built to be drastically more cost-effective than any of the existing solutions.

👉 Apply here for early access
We’ll be onboarding in phases and working closely with early users. Limited slots.


Follow on X Follow on LinkedIn Join our Discord

Crawl4AI turns the web into clean, LLM ready Markdown for RAG, agents, and data pipelines. Fast, controllable, battle tested by a 50k+ star community.

✨ Check out latest update v0.9.3

New in v0.9.3: Security release. Closes five coordinated-disclosure advisories: arbitrary file write, SSRF, and denial of service in the PDF processing path, plus two XSS issues in the Docker Playground. Also ships 33 bug fixes across the Docker server, crawler, and PDF handling. No new features, no breaking changes. Release notes →

✨ Recent v0.9.2: Maintenance patch release. Fixes a MemoryAdaptiveDispatcher task/page leak when a streaming crawl is closed, Docker Playground "Advanced Config" and Monitor WebSocket auth, Playwright headless-shell packaging, and GPU (ENABLE_GPU=true) Docker builds. Release notes →

✨ Recent v0.9.0: Major secure-by-default release of the Docker API server. Auth is on by default, the server binds loopback unless given a token, and the request body is now an untrusted trust boundary. Release notes →

✨ Recent v0.8.7: Security-hardening release. Fixes critical Docker API vulnerabilities (RCE, SSRF, auth bypass, file write, XSS, hardcoded JWT secret), adds DomainMapper, and ships scraping, deep-crawl, and LLM fixes. Release notes →

✨ Previous v0.8.0: Crash Recovery & Prefetch Mode! Deep crawl crash recovery with resume_state and on_state_change callbacks for long-running crawls. New prefetch=True mode for 5-10x faster URL discovery. Release notes →

✨ Previous v0.7.8: Stability & Bug Fix Release! 11 bug fixes addressing Docker API issues, LLM extraction improvements, URL handling fixes, and dependency updates. Release notes →

🤓 My Personal Story

I grew up on an Amstrad, thanks to my dad, and never stopped building. In grad school I specialized in NLP and built crawlers for research. That’s where I learned how much extraction matters.

In 2023, I needed web-to-Markdown. The “open source” option wanted an account, API token, and $16, and still under-delivered. I went turbo anger mode, built Crawl4AI in days, and it went viral. Now it’s the most-starred crawler on GitHub.

I made it open source for availability, anyone can use it without a gate. Now I’m building the platform for affordability, anyone can run serious crawls without breaking the bank. If that resonates, join in, send feedback, or just crawl something amazing.

Why developers pick Crawl4AI
  • LLM ready output, smart Markdown with headings, tables, code, citation hints
  • Fast in practice, async browser pool, caching, minimal hops
  • Full control, sessions, proxies, cookies, user scripts, hooks
  • Adaptive intelligence, learns site patterns, explores only what matters
  • Deploy anywhere, zero keys, CLI and Docker, cloud friendly

🚀 Quick Start

  1. Install Crawl4AI:
# Install the package
pip install -U crawl4ai

# For pre release versions
pip install crawl4ai --pre

# Run post-installation setup
crawl4ai-setup

# Verify your installation
crawl4ai-doctor

If you encounter any browser-related issues, you can install them manually:

python -m playwright install --with-deps chromium
  1. Run a simple web crawl with Python:
import asyncio
from crawl4ai import *

async def main():
    async with AsyncWebCrawler() as crawler:
        result = await crawler.arun(
            url="https://www.nbcnews.com/business",
        )
        print(result.markdown)

if __name__ == "__main__":
    asyncio.run(main())
  1. Or use the new command-line interface:
# Basic crawl with markdown output
crwl https://www.nbcnews.com/business -o markdown

# Deep crawl with BFS strategy, max 10 pages
crwl https://docs.crawl4ai.com --deep-crawl bfs --max-pages 10

# Use LLM extraction with a specific question
crwl https://www.example.com/products -q "Extract all product prices"

💖 Support Crawl4AI

🎉 Sponsorship Program Now Open! After powering 51K+ developers and 1 year of growth, Crawl4AI is launching dedicated support for startups and enterprises. Be among the first 50 Founding Sponsors for permanent recognition in our Hall of Fame.

Crawl4AI is the #1 trending open-source web crawler on GitHub. Your support keeps it independent, innovative, and free for the community — while giving you direct access to premium benefits.

Become a Sponsor
Current Sponsors

🤝 Sponsorship Tiers

  • 🌱 Believer ($5/mo) — Join the movement for data democratization
  • 🚀 Builder ($50/mo) — Priority support & early access to features
  • 💼 Growing Team ($500/mo) — Bi-weekly syncs & optimization help
  • 🏢 Data Infrastructure Partner ($2000/mo) — Full partnership with dedicated support
    Custom arrangements available - see SPONSORS.md for details & contact

Why sponsor?
No rate-limited APIs. No lock-in. Build and own your data pipeline with direct guidance from the creator of Crawl4AI.

See All Tiers & Benefits →

✨ Features

📝 Markdown Generation
  • 🧹 Clean Markdown: Generates clean, structured Markdown with accurate formatting.
  • 🎯 Fit Markdown: Heuristic-based filtering to remove noise and irrelevant parts for AI-friendly processing.
  • 🔗 Citations and References: Converts page links into a numbered reference list with clean citations.
  • 🛠️ Custom Strategies: Users can create their own Markdown generation strategies tailored to specific needs.
  • 📚 BM25 Algorithm: Employs BM25-based filtering for extracting core information and removing irrelevant content.
📊 Structured Data Extraction
  • 🤖 LLM-Driven Extraction: Supports all LLMs (open-source and proprietary) for structured data extraction.
  • 🧱 Chunking Strategies: Implements chunking (topic-based, regex, sentence-level) for targeted content processing.
  • 🌌 **Cosin

readme truncated — read the full docs on github

Frequently asked questions

Is Crawl4AI free to use?

Crawl4AI is open source under the Apache-2.0 licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does Crawl4AI do?

LLM-ready web crawler built for AI data pipelines

What is Crawl4AI written in?

Crawl4AI is primarily written in Python. Its source is publicly available at https://github.com/unclecode/crawl4ai, and it has 83,747 GitHub stars.