LLMs struggle with eCommerce sites because: 1⃣ Product pages are HTML-heavy and noisy 2⃣ Catalogs change faster than LLMs can re-crawl 3⃣ Context windows can’t handle full category dumps

Our solution: A fork of Answer.AI’s llms.txt that introduces site-llms.xml – an XML sitemap protocol for product data. Stores expose:

/site-llms.xml: Index of all product URLs

/product/123/llms.txt: Clean Markdown with specs/pricing (example in repo)

Benefits: AI gets structured data instead of scraping Stores control what’s exposed (like robots.txt) Scales to millions of products (sitemap indexes supported)

We’re open-sourcing this under CC BY-SA (same as sitemap protocol). Would love HN’s thoughts:

Is this the right abstraction? Could it work for non-eCommerce sites?

Repo: github.com/Lumigo-AI/site-llms (stars welcome!)