How do I create an llms.txt file?

Paste your sitemap into the generator, set a name and a one-line summary, edit the sections and link titles, then download the file and upload it to the root of your site so it answers at /llms.txt.

What does an llms.txt example look like?

“# Acme”, then “> Invoicing for freelancers.”, then “## Docs” followed by “- [API reference](https://acme.io/docs/api.md): endpoints and auth”, and “## Optional” for links an agent can skip, such as the blog.

Where do I put llms.txt?

At the root of your site, at /llms.txt. Version 2 of the proposal also allows a file under a path, such as /docs/llms.txt, which covers the pages under that path; agents use the most specific file.

Does Google use llms.txt?

No. Google says Google Search ignores llms.txt and similar files, and that keeping one neither harms nor helps your visibility or rankings in Search. Other services may read it.

What is the Optional section in llms.txt?

A section named Optional, by convention, for secondary links an agent can skip when it needs a shorter context. Since version 2 it carries no special meaning for tools.

Should llms.txt links be absolute URLs?

The spec does not require it, but every example in it uses full URLs, and an agent can follow those without knowing where the file sits. The validator flags relative links as a warning.

What is the difference between llms.txt and robots.txt?

robots.txt tells crawlers what they may access. llms.txt allows or blocks nothing: it is a curated guide an agent reads when it needs information about your site.

Free SEO tool

llms.txt generator and validator

Paste your sitemap or a list of URLs, edit the sections and link titles, and download an llms.txt file in the llmstxt.org format. Already have one? Check it against the spec.

Updated October 27, 2026

Quick answer

What is an llms.txt file and what goes in it?

llms.txt is a markdown file at /llms.txt that tells AI agents what your site is and which pages to read. In order: an H1 with the site name (the only required part), a blockquote summary, optional details, then H2 sections of links written as - [Title](https://url): note. A section called Optional holds links an agent can skip.

How to make an llms.txt file

Paste your URLs
Open yoursite.com/sitemap.xml and paste it, or paste any list of URLs. The generator groups them into sections by the first part of the path.
Write the top
Set the site name and a one-sentence summary, and add details such as prices and limits if agents need them.
Edit the links
Rename sections, fix link titles, add short notes, untick pages that do not help, and mark sections such as the blog as Optional.
Publish and check
Copy or download the file, put it at yoursite.com/llms.txt, then paste it into Validate to check it against the format.

How the generator and validator work

The generator reads every <loc> in a sitemap, or every http and https URL in a pasted list, and drops repeats. It groups URLs by the first segment of their path, so /docs/api and /docs/start land in Docs, and writes a title from each slug: /blog/launch-week becomes “Launch week”. Top-level pages such as /pricing share the first section.

The output follows the llmstxt.org format in its order: the H1, the summary as a blockquote, the details, then one H2 per section with a list of links. Every section you mark Optional is written under a single Optional heading at the end. Square brackets in titles become round ones and brackets in URLs are percent-encoded, so no parser cuts a link short.

The validator reads a file line by line the way the proposal describes it and the way its sample JavaScript parser reads it: list items start with a dash, a title cannot contain ], a URL cannot contain ), and only the first line of the summary counts. It reports errors that break the format, warnings that a parser may misread, and notes.

Worked example

Input: https://acme.io/, /pricing, /docs/api, /docs/start, /blog, /blog/launch-week.
Top-level pages / and /pricing go to the first section, Pages: “Home” and “Pricing”.
/docs/api and /docs/start share the first segment docs, so they form ## Docs: “Api” and “Start”.
/blog has deeper pages, so it joins /blog/launch-week in Blog, which starts marked Optional.
Output: # Acme, the > summary, ## Pages, ## Docs, then ## Optional with the two blog links.

What the validator checks

Check	Why
An H1 on the first line	The H1 with the site or project name is the only required part of the format.
A blockquote summary after the H1	Optional, but it is the short description an agent reads first. The sample parser reads one line.
No headings in the details	The format allows any markdown there except headings.
H2 sections holding lists of links	Each item is - [name](url), optionally followed by a colon and notes.
Dash bullets, no ] in titles, no ) in URLs	The proposal’s sample parser reads only items in that shape.
Valid, full URLs	The spec’s examples use absolute URLs, which an agent can follow without knowing where the file sits.
Duplicate links and empty sections	Repeats waste the agent’s context; an empty section adds nothing.

Who reads llms.txt

Google says Google Search does not use llms.txt and that having one neither helps nor harms your visibility in Search. The proposal’s author says coding agents use these files reliably, mostly on software documentation, and AI labs publish them for their own developer docs. Treat it as a cheap guide for agents, not a ranking factor.

llms.txt questions

What is an llms.txt file?: A markdown file at /llms.txt that gives AI agents a short summary of a site and links to the pages worth reading. Jeremy Howard proposed it in September 2024; version 2 of the proposal was published in August 2026.
How do I create an llms.txt file?: Paste your sitemap into the generator, set a name and a one-line summary, edit the sections and link titles, then download the file and upload it to the root of your site so it answers at /llms.txt.
What does an llms.txt example look like?: “# Acme”, then “> Invoicing for freelancers.”, then “## Docs” followed by “- [API reference](https://acme.io/docs/api.md): endpoints and auth”, and “## Optional” for links an agent can skip, such as the blog.
Where do I put llms.txt?: At the root of your site, at /llms.txt. Version 2 of the proposal also allows a file under a path, such as /docs/llms.txt, which covers the pages under that path; agents use the most specific file.
Does Google use llms.txt?: No. Google says Google Search ignores llms.txt and similar files, and that keeping one neither harms nor helps your visibility or rankings in Search. Other services may read it.
What is the Optional section in llms.txt?: A section named Optional, by convention, for secondary links an agent can skip when it needs a shorter context. Since version 2 it carries no special meaning for tools.
Should llms.txt links be absolute URLs?: The spec does not require it, but every example in it uses full URLs, and an agent can follow those without knowing where the file sits. The validator flags relative links as a warning.
What is the difference between llms.txt and robots.txt?: robots.txt tells crawlers what they may access. llms.txt allows or blocks nothing: it is a curated guide an agent reads when it needs information about your site.

Cite this tool

Free to link and quote. Use this reference:

SaaSCity, "llms.txt Generator & Validator", October 27, 2026. https://saascity.io/free-tools/llms-txt-generator

llms.txt generator and validator

Your site

What is an llms.txt file and what goes in it?

How to make an llms.txt file

How the generator and validator work

Worked example

What the validator checks

Who reads llms.txt

llms.txt questions

Cite this tool

Sources

Your site

What is an llms.txt file and what goes in it?

How to make an llms.txt file

How the generator and validator work

Worked example

What the validator checks

Who reads llms.txt

llms.txt questions

Related

Cite this tool

Sources