llms.txt
llms.txt is an optional Markdown file at a site's root that lists your most important pages for AI tools. Coding agents can use it as a map. Google Search ignores it, and there is no proven link between having one and being cited by AI.
By Tal Gerafi
AEO/GEOLast updated
llms.txt is a plain Markdown file you publish at your site's root (/llms.txt). It lists the pages that matter most, such as docs, product overviews and key guides, with a short note on each. It was proposed in September 2024 and is still a proposal, not a standard. Its real users today are coding agents and developer tools that fetch it by name. There is no evidence that it helps your site get ranked or cited in AI search.
How it works
The file lives at https://yoursite.com/llms.txt. It is written in Markdown, so a person and a machine can both read it. The convention is simple: an H1 with your site name, an optional short summary in a blockquote, then H2 sections holding lists of links. Each link has a short note on what the page covers.
A normal HTML page wraps its content in navigation, scripts and styling. A tool that reads llms.txt gets the URLs that matter in plain words, without parsing any of that. Some sites also publish an llms-full.txt that inlines the page text, so a tool can read it in one fetch.
Who actually reads it
Mostly coding agents and IDE tools. A developer can point Claude Code or Cursor at a docs site's llms.txt and get a clean, cheap map of the docs. That is a real benefit for SaaS products with API documentation.
Search is a different story. Google's AI optimization guide says Google Search ignores llms.txt and similar files, and that creating one "will neither harm nor help" your visibility. An SE Ranking study of about 300,000 domains (November 2025) found that having the file did not make a domain more likely to be cited by AI models. We have seen no public evidence that ChatGPT or Perplexity use it to choose sources. Their AI crawlers read your normal pages.
Should a B2B site ship one?
Only if it costs you nothing. On a Next.js site it can be generated from your content in a few lines and stays current on its own. That is why we keep one on greeto.studio. Don't pay for it as a service, and don't expect it to change your AI visibility.
If being cited is the goal, the work is in the pages: clear answers near the top, crawlable HTML, accurate facts and sources. Our guide on how to rank in ChatGPT and Perplexity covers that, and does llms.txt help with ChatGPT goes deeper on the file itself.
FAQ
Is llms.txt an official standard?
No. llms.txt is a proposed convention, not a ratified standard, and no search engine or model is obliged to read it. Treat it as an optional courtesy file, not part of your answer engine optimization plan.
Does Google use llms.txt?
Not for Google Search. Google says Google Search ignores the file and that it will neither harm nor help your visibility. For ChatGPT and Perplexity, see does llms.txt help ChatGPT.
What is the difference between llms.txt and llms-full.txt?
llms.txt is the index: links to your key pages, each with a short note. llms-full.txt inlines the page text as well, so a tool can read the content without a second fetch. Both are optional, and neither is used by Google Search.
