lumpinif/deepcrawl

100% free and full open-source edge Firecrawl alternative with better links extraction for agents - that you can deploy to cloudflare or vercel by yourself.

63
/ 100
Established

This tool helps AI agents gather specific information from websites efficiently. It takes publicly accessible web pages as input and provides clean, structured content in Markdown, along with a hierarchical list of links and other metadata. This makes it easier for AI models to understand website content without generating irrelevant information, benefiting AI developers or anyone building AI agents that need to process web data.

568 stars. Available on npm.

Use this if you are building AI agents that need to quickly and accurately extract specific, cleaned content and structured links from many public websites.

Not ideal if your primary goal is to bypass anti-scraping measures or extract data from websites that require complex authentication.

AI agent development web data extraction large language model (LLM) data preparation content summarization information retrieval
Maintenance 10 / 25
Adoption 10 / 25
Maturity 24 / 25
Community 19 / 25

How are scores calculated?

Stars

568

Forks

65

Language

TypeScript

License

MIT

Category

scraper

Last pushed

Mar 12, 2026

Commits (30d)

0

Dependencies

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/perception/lumpinif/deepcrawl"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.