Anakin-Inc/anakin
Open-source web scraping API. Turn any website into clean markdown or structured JSON. Anti-detect browser, proxy auto-selection, self-hosted. One command: make up
This tool helps you quickly and reliably get information from any website, even complex ones, and turn it into clean text or organized data. You provide a web address, and it gives you back either an easy-to-read markdown version of the page content, or structured JSON data extracted by AI. It's designed for anyone who needs to gather large amounts of web data for tasks like populating AI models, competitive analysis, or market research.
Use this if you need a dependable way to automatically collect clean, structured data or text from many different websites without getting blocked or dealing with inconsistent page layouts.
Not ideal if you only need to scrape a handful of simple, static websites manually or if you prefer using a managed cloud service rather than hosting your own solution.
Stars
18
Forks
1
Language
Go
License
AGPL-3.0
Category
Last pushed
Apr 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/perception/Anakin-Inc/anakin"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
seleniumbase/SeleniumBase
APIs for browser automation, testing, and bypassing bot-detection.
apify/crawlee-python
Crawlee—A web scraping and browser automation library for Python to build reliable crawlers....
intoli/user-agents
A JavaScript library for generating random user agents with data that's updated daily.
apify/crawlee
Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In...
Kaliiiiiiiiii-Vinyzu/patchright
Undetected version of the Playwright testing and automation library.