Learn · How AI answers
What is llms.txt, and do AI engines actually read it?
By Cloute · Published October 2, 2026
The short answer
llms.txt is a proposed plain-text file, placed at the root of a website, that gives AI systems a short summary of the site and links to its most useful pages. It was proposed in September 2024 and is not an adopted standard. The evidence so far is that the major AI search crawlers rarely request it, so it does not decide whether ChatGPT, Gemini or Perplexity name a business. What decides that is whether the engine can open and read your ordinary pages. Across 64,441 AI answers about local businesses, engines named a business 84% of the time when they had opened one of its own pages while answering, and 16% when they had not.
What goes in an llms.txt file
The proposal, published at llmstxt.org by Jeremy Howard, describes a Markdown file served at /llms.txt with a fixed order:
- A top-level heading with the name of the site or project. This is the only required part.
- A short summary in a block quote.
- Optional paragraphs with more detail.
- Sections, each a second-level heading followed by a list of links with a short note on each.
- A section titled Optional, by convention, for links a system can skip when it needs a shorter version.
The proposal also suggests offering a clean Markdown version of important pages at the same address with .md added.
llms.txt, robots.txt and sitemap.xml are different things
| File | What it does | Who acts on it |
|---|---|---|
| robots.txt | Tells crawlers which pages they may and may not fetch | Search and AI crawlers that honour it, including OpenAI's, Anthropic's and Perplexity's declared crawlers |
| sitemap.xml | Lists the pages you want found | Search engines such as Google and Bing |
| llms.txt | Suggests which pages matter most and summarises the site | Mostly developer tools and coding assistants today. No major AI search engine has said it relies on it |
Do AI engines read llms.txt?
- Google's John Mueller has compared llms.txt to the keywords meta tag and said that no AI system currently uses it. Google's Gary Illyes said in July 2025 that Google does not support it.
- An Ahrefs analysis published in 2026 found that 97% of llms.txt files received no requests at all in a month.
- Cloute's own site publishes one. In its first two days of crawler logging, about 400 requests came from search and AI crawlers, and 1 of them asked for /llms.txt. It came from GPTBot. That is a small sample, and it points the same way.
- Where it is used: documentation sites, and coding assistants that are pointed at a library's llms.txt to load its documentation.
Should a business add one?
It is cheap and harmless, so there is no reason not to. There is also no evidence it changes what AI engines say about a business. Treat it as a courtesy to tools that look for it, not as the thing that gets you named.
What matters more than llms.txt
- robots.txt that does not block the AI search crawlers: OAI-SearchBot, ChatGPT-User, Claude-User, PerplexityBot.
- Bot protection that lets verified AI crawlers through. In our tests far more sites turned an automated visitor away at the firewall than in robots.txt.
- Facts in the page source. Most AI crawlers do not run JavaScript.
- Pages that answer the questions customers ask, in plain sentences.
- Measuring which business the engines actually name, on the same questions over time.
Read next
AI crawlers: which ones read your website Should I block AI crawlers? Study: can AI read local business websites? ChatGPT SEO: how to rank in ChatGPT AEO strategy in six stepsQuestions people ask
What is llms.txt?
A proposed Markdown file at the root of a website that summarises the site for AI systems and links to its most useful pages. People search Google for "llms.txt" about 5,400 times a month in the United States. Search volumes are average monthly Google searches in the United States, from Google Ads keyword data, October 2026.
Does llms.txt help you rank in ChatGPT?
There is no evidence that it does. OpenAI has not said ChatGPT uses it, and server logs show AI crawlers rarely request it. ChatGPT names businesses whose ordinary pages it can open and read.
Is llms.txt the same as robots.txt?
No. robots.txt tells crawlers what they may fetch, and crawlers act on it. llms.txt is a suggestion of what to read, and almost nothing acts on it yet.
Do I need an llms.txt generator?
No. The file is short enough to write by hand: a heading, a one-paragraph summary, and a list of links to your most important pages with a line about each.
Does Google use llms.txt?
No. Google has said it does not support llms.txt for Search or AI Overviews, and that the same SEO fundamentals apply to its AI features.
About Cloute. Cloute is an AI visibility company for local businesses. It measures how often ChatGPT, Gemini, Claude, Perplexity and Google AI Overviews recommend a business against its local competitors, and works every month to move it to the top.