llms.txt is a plain-markdown file at the root of your site — yoursite.com/llms.txt — that tells AI assistants what your site is and which pages matter. It is a proposed standard from llmstxt.org, and it is curated rather than complete: a short description of the site followed by grouped links to the pages you actually want an assistant to read.

How do I create an llms.txt file?

Enter your domain in the generator above. It reads your homepage metadata and your sitemap, groups your URLs into sections, fetches the real title of each page, and returns a formatted llms.txt. Then cut anything you would not want an assistant to quote, and upload the file to your site root so it answers at yoursite.com/llms.txt.

Where do I put the llms.txt file?

At the root of your domain, so it is served at yoursite.com/llms.txt as plain text. On Next.js put it in /public. On WordPress upload it to the root folder over SFTP or use a file-manager plugin. On Shopify and Webflow, where the site root is not writable, serve it through a redirect or a custom route rather than a page — a file that returns HTML does not count.

How is llms.txt different from robots.txt and sitemap.xml?

robots.txt is permission — which crawlers may fetch what. sitemap.xml is inventory — every URL you have. llms.txt is editorial: a short description of what your site is, then the handful of pages you would point someone at. It is the only one of the three that says what your site is for rather than what it contains.

Will publishing llms.txt improve my AI visibility?

Partly, and it is worth being precise about which part. It removes ambiguity about what your site is and which pages are canonical, which helps an assistant that has already reached you. It does not make assistants reach you, and it does not make them recommend you when someone asks for the best option in your category — that comes from being cited on sources they already trust. Publish it because it is an afternoon of work, then measure whether anything changed.

Does anything here use AI to write my llms.txt?

No. Every line comes from your own site — your metadata, your sitemap, and the real titles of your pages. Nothing is generated by a model, so the file cannot describe a page you do not have or claim something your site does not say.

Free tool

llms.txt generator

Generate the index AI crawlers read, from your site's own metadata and sitemap. No account, no card.

We read your homepage and sitemap. Nothing is stored, and no AI writes any of it.

What is llms.txt?

llms.txt is a plain-markdown file at the root of your site — yoursite.com/llms.txt — that tells AI assistants what your site is and which pages matter. It is a proposed standard from llmstxt.org, and the point of it is that it is curated: a short description of the site, then grouped links to the pages you would actually point someone at.

What an llms.txt file looks like

An H1 with the site name, a blockquote summarising it in a sentence or two, then ## sections of links, each with a short note on what the page is for. That last part carries most of the value — a link with no description is a URL, and an assistant has to open it to find out what it was.

# Acme Analytics

> Product analytics for B2B SaaS teams. Track activation, retention and
> expansion without a data warehouse.

## Product

- [Product overview](https://acme.com/product): What Acme does and who it is for
- [Pricing](https://acme.com/pricing): Plans, limits and what each tier includes
- [Integrations](https://acme.com/integrations): Supported data sources

## Docs

- [Getting started](https://acme.com/docs/start): Install and first event
- [API reference](https://acme.com/docs/api): Endpoints and authentication

## Company

- [About](https://acme.com/about): Team, funding and where we are based

How to create an llms.txt file

1Enter your domain. Paste your homepage URL into the generator. No account and no card.
2We read your site. We fetch your homepage metadata and your sitemap, group the URLs into sections, and pull the real title of each page.
3Cut what does not belong. A sitemap lists everything, including pages you would not choose to put in front of an assistant. llms.txt is valuable because it is curated, so remove anything you would not quote yourself.
4Publish it at your site root. Upload the file so it is served as plain text at yoursite.com/llms.txt.
5Check that a crawler can actually read it. A file behind a redirect, a login, or a bot rule is a file that does not exist. Request it as GPTBot and ClaudeBot to confirm.

Where to put it, by platform

It has to answer at your root as plain text. The awkward cases are the hosted builders, where the root is not yours to write to.

Platform	Where the file goes
Next.js	Drop llms.txt into /public. It is served at the root automatically.
WordPress	Upload to the site root over SFTP, or use a file-manager plugin. Do not create a page called llms — that returns HTML.
Shopify	The site root is not writable. Serve it from a redirect or an app proxy so the URL returns plain text.
Webflow	No root file uploads. Use a reverse proxy in front of the site, or host the file on a subdomain you control and redirect.
Framer	Add it as a custom route that returns text/plain, not as a published page.
Static hosting (S3, Netlify, Vercel)	Copy it into the published output directory alongside robots.txt.

llms.txt vs robots.txt vs sitemap.xml

They are three different jobs, and publishing one does not replace another.

File	Answers	Written for
robots.txt	What may I fetch?	Every crawler
sitemap.xml	What pages exist?	Search engines
llms.txt	What is this site for?	AI assistants

robots.txt is permission and sitemap.xml is inventory. llms.txt is the only one that is editorial — the only one that says what your site is for rather than what it contains.

Does llms.txt actually improve AI visibility?

Partly, and it is worth being precise about which part, because we are the ones who measure the difference.

It removes ambiguity for an assistant that has already reached you — what the site is, which page is canonical, what to quote. That is real, and it costs an afternoon.

What it does not do is make assistants reach you, or make them name you when a buyer asks who the best option in your category is. That comes from being cited on the sources those models already trust. Publishing llms.txt and expecting to be recommended is like fixing your title tags and expecting to rank first — necessary, not sufficient.

Frequently asked questions

What is llms.txt?: llms.txt is a plain-markdown file at the root of your site — yoursite.com/llms.txt — that tells AI assistants what your site is and which pages matter. It is a proposed standard from llmstxt.org, and it is curated rather than complete: a short description of the site followed by grouped links to the pages you actually want an assistant to read.
How do I create an llms.txt file?: Enter your domain in the generator above. It reads your homepage metadata and your sitemap, groups your URLs into sections, fetches the real title of each page, and returns a formatted llms.txt. Then cut anything you would not want an assistant to quote, and upload the file to your site root so it answers at yoursite.com/llms.txt.
Where do I put the llms.txt file?: At the root of your domain, so it is served at yoursite.com/llms.txt as plain text. On Next.js put it in /public. On WordPress upload it to the root folder over SFTP or use a file-manager plugin. On Shopify and Webflow, where the site root is not writable, serve it through a redirect or a custom route rather than a page — a file that returns HTML does not count.
How is llms.txt different from robots.txt and sitemap.xml?: robots.txt is permission — which crawlers may fetch what. sitemap.xml is inventory — every URL you have. llms.txt is editorial: a short description of what your site is, then the handful of pages you would point someone at. It is the only one of the three that says what your site is for rather than what it contains.
Will publishing llms.txt improve my AI visibility?: Partly, and it is worth being precise about which part. It removes ambiguity about what your site is and which pages are canonical, which helps an assistant that has already reached you. It does not make assistants reach you, and it does not make them recommend you when someone asks for the best option in your category — that comes from being cited on sources they already trust. Publish it because it is an afternoon of work, then measure whether anything changed.
Does anything here use AI to write my llms.txt?: No. Every line comes from your own site — your metadata, your sitemap, and the real titles of your pages. Nothing is generated by a model, so the file cannot describe a page you do not have or claim something your site does not say.

Check the file is readable

A file behind a redirect, a login, or a bot rule is a file that does not exist. Request your site as GPTBot, ClaudeBot and PerplexityBot and see what each one actually gets.

Free AI crawler check