devtools

crawl4ai

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
85,093 stars+463★ this week8,824 forksPythonInstall verified Sep 14Updated 10/5/2026100% free · open source
What it does

Crawl4AI lets you fetch a web page and have an LLM extract the clean, structured content you need with a single Python call or CLI command.

When to use it
  • •You need to pull product details, FAQs, or pricing tables from competitor sites for market research.
  • •You want to feed fresh web content into a generative AI prompt without manual copy‑pasting.
  • •You must automatically summarize news articles or blog posts for a daily briefing email.
Ready-to-paste prompt
crawl4ai -u https://stripe.com/pricing -m gpt-4o --output json > stripe_pricing.json
Heads up: Crawl4AI requires an LLM API key (e.g., OPENAI_API_KEY) and will fail with a 401 error if the env var is missing or the key lacks the needed model access.
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup✓ Install verified 9/14/2026

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/crawl4ai && curl -fsSL https://workflowstacks.com/api/skills/crawl4ai/claude-skill -o ~/.claude/skills/crawl4ai/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How crawl4ai works
Codeflow
Free to inspect

Crawl4ai is a very large Python project (~109k lines across 282 code files, plus 242 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~109k lines · 282 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python · Docker
No API keys detected
Python 99%JavaScript 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    crawl4ai/cli.py
    Where the program starts running
  3. 3
    pyproject.toml
    Dependencies and the commands it exposes
  4. 4
    crawl4ai/__init__.py
    Inside crawl4ai/ — the main logic begins here
What's in each folder
crawl4ai/Core code — the actual logic83 files
prompts/Prompts, skills & agent definitions1 files
docs/Documentation496 files
deploy/Deployment / infrastructure68 files
sbom/Folder2 files
scripts/Helper scripts2 files
tests/Tests — proof it works218 files
.github/CI / automation (GitHub Actions)14 files
READMEHas testsDocumentedCI checksDocker readyApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
unclecode
Language
Python
Category
devtools
Published
5/9/2024

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/crawl4ai.svg)](https://workflowstacks.com/skills/crawl4ai?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.