Urgent.News

What's breaking now, across thousands of outlets.

AI

What Is llms.txt? How to Set It Up on WordPress (2026 Guide)

In September 2024, Jeremy Howard — the guy behind fast.ai and a former president of Kaggle — published a short proposal. He called it llms.txt, and the idea was almost annoyingly simple: give AI models a plain-text map of your website so they don't have to guess what's important. No one paid much attention at first. Then Cloudflare added one. Then Stripe. Then Anthropic, Vercel, Supabase, and…

In September 2024, fast.ai's Jeremy Howard introduced llms.txt, a proposal that aims to give AI models a plain-text map of a website. No one paid much attention initially, but then major companies like Cloudflare, Stripe, Anthropic, Vercel, Supabase, and Zapier began using it. Over 780 websites now have an llms.txt file, with three community directories tracking adoption.

To understand an AI model's perspective, imagine ChatGPT or Perplexity trying to answer a question about your product. They crawl your HTML, which includes headers, footers, navigation menus, and various widgets. This noise makes it difficult to identify the important content. llms.txt simplifies this process by providing a structured Markdown file (located at yoursite.com/llms.txt) that acts as a curated table of contents for AI models.

The format is simple: it includes a one-line summary of the site, a brief description, and H2 sections with links to key pages. For example, Stripe organizes their llms.txt by product category, while Cloudflare structures theirs by product line. Anthropic goes a step further by maintaining both an llms.txt and an llms-full.txt, which contains the full Markdown content of their key pages.

While some websites report no measurable change or even a decline in AI traffic after implementing llms.txt, early adopters have a clear advantage. With only 0.3% of top websites having an llms.txt file, first-movers can establish a baseline that later standards build upon. Setting up llms.txt takes only a few minutes and has no downsides.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Research Dossier: An Agent That Shows Its Disagreements Instead of Hiding Them

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content . What I Built Research Dossier is a multi-agent research analyst built with LangGraph .

  • Research Dossier is a multi-agent research analyst
  • Uses Sanity Knowledge Base for information management
  • Displays disagreements between sources instead of hiding them

More from Sunday 20 September →