Five open-source repos that handle scraping, parsing, repo-to-text, PR review and multi-LLM routing without a single subscription.
What's inside
by Divjot Sahni · EZYE Consulting · ezye.com.au
The repos at a glance
gitingest — turns any repo into LLM-ready text in seconds
crawl4ai — scrapes the web for your agents without the usual headaches
docling — parses PDFs and docs into clean structured data
And two more that quietly replace tools you already pay for...
Why these beat the paid versions
No subscriptions, no waitlists, no API lock-in
Each one maps to a specific job in an AI workflow
The real win is chaining them together — here's the stack...
Free access — enter your email below