Join
2
1 Comment

I built a site that finds book recommendations from tweets using Grok's X Search API

by Maxence Cornet

I wanted book recommendations from people I follow, but most sites just list books without any source.

So I built a site that searches public tweets for book recommendations using Grok's x_search API.

How it works:

  • Uses Grok API with the x_search tool to search X/Twitter
  • Extracts book mentions from tweets containing "great read", "must read", "favorite book", etc.
  • Each recommendation links back to the original tweet as a source

Tech stack: Astro, Python extraction script, Grok 4 API with x_search, Cloudflare Pages

Currently tracking 150+ personalities with 1000+ book recommendations, all sourced from real tweets.

Check it out here

Would love feedback on the UX or suggestions on how to improve!

Avatar for Maxence Cornet Maxence Cornet
on January 16, 2026
Say something nice to maxencec…
Post Comment
  1. 1

    Nice! Using the x_search API as a data source is clever — it eliminates the rate-limit and structure-change headaches you'd hit with traditional scrapers. The 'extract from unstructured text' step is where most of these projects fail. Are you using Grok's LLM for the extraction, or custom parsing logic?

    User Avatar misprice
    ·
    3 hours ago
    ·
    Reply
Trending on Indie Hackers
710% Growth on my tiny productivity tool hit differently, here is what worked in January User Avatar 34 comments You roasted my MVP. I listened. Here is v1.3 (Crash-proof & 100% Local) User Avatar 25 comments Why I built a 'dumb' reading app in the era of AI and Social Feeds User Avatar 16 comments Our clients have raised over $ 2.5 M in funding. Here’s what we actually do User Avatar 9 comments How do I find these first 5-10 members? User Avatar 3 comments