🕷️CrawlForge

Extract Data from Any Website with AI

Tell CrawlForge what data you need in plain English. Our AI-powered crawler extracts structured data and stores it directly in your database.

🤖 AI-Powered Extraction

Describe what you want to extract in plain English. The LLM understands your intent and extracts exactly what you need.

🗄️ Direct to Database

Results go straight into your Supabase tables. Define your schema once, get structured data automatically.

Scheduled Crawls

Set up recurring crawls with cron schedules. Keep your data fresh without lifting a finger.

🔒 Multi-Tenant

Create workspaces for different projects or teams. Row-level security keeps your data isolated.

🏠 Self-Hostable

Run on your own infrastructure with Ollama for local LLMs. Your data never leaves your servers.

📊 Full Visibility

Track every crawl run, see what was extracted, and debug issues with detailed logs.

How It Works

Example extraction prompt:

Extract job postings from this page.
For each job, return:
- title: Job title
- company: Company name  
- location: City or "Remote"
- salary_min: Minimum salary (number)
- salary_max: Maximum salary (number)
- url: Link to full posting