Skip to content
Tityra
Login
Start for free
HomeAboutWho It's For
  • Publishers & Media
  • Ecommerce & Retail
  • SaaS & Technology
  • Agencies
  • Government & Public Sector
  • Financial Services & Insurance
PricingFAQBlog
info@tityra.com
XLinkedIn
  1. Home
  2. /
  3. Blog
  4. /
  5. Content access

What is llms.txt, and does your website need it?

Learn what llms.txt does, which tools use it and how to decide whether it is worth maintaining on your website.

6 min read

Doğu Abaris · 22 November 2026

Read the article

Used by many

  • Onedio
  • Maçkolik
  • Webtekno
  • Yemek.com
  • Mynet
5/51 review on G2
Start for free

UNDERSTAND CONTENT DELIVERY

Learn what a tested client receives.

FOLLOW THE EVIDENCE

See how observations become findings.

PUT GUIDANCE INTO PRACTICE

Find changes your team can investigate.

Read the article

In this article

What is llms.txt?What does an llms.txt file contain?Does your website need llms.txt?Does llms.txt improve Google Search visibility?Which tools actually use llms.txt?How llms.txt differs from a sitemap and robots.txtHow to create an llms.txt fileCheck that tools can read the pages you listHow to test whether the file helpsKeep the index current
Table of Contents
What is llms.txt?What does an llms.txt file contain?Does your website need llms.txt?Does llms.txt improve Google Search visibility?Which tools actually use llms.txt?How llms.txt differs from a sitemap and robots.txtHow to create an llms.txt fileCheck that tools can read the pages you listHow to test whether the file helpsKeep the index current

Copy linkWhat is llms.txt?

llms.txt is a plain-text file that summarises a website for AI agents and links to its key pages. The format is still an open proposal, so publishing it is optional and support varies by tool.[1][7]

The file uses Markdown, a plain-text format for headings and links. You can open a published file directly in your browser by adding /llms.txt to the domain.[1]

Copy linkWhat does an llms.txt file contain?

The proposal starts with the website or project name as the main heading. You can add a short description, group links by topic and describe what each page covers.[1]

This shortened extract from Shopify's public llms.txt shows how the file groups links to help pages under headings.[13]

Shopify llms.txt excerpt
# Shopify

## Sell Internationally

- [International settings](https://help.shopify.com/en/manual/international)

## Need help?

- [Shopify Help Center](https://help.shopify.com/en/)

Copy linkDoes your website need llms.txt?

Give an AI assistant your website address and ask it a question visitors already ask. If it reaches the right page and gives the correct answer, you can skip the file for that task.

If the assistant can read the page when you give it the link but struggles to find it from the homepage, try a short index. If the destination page leaves out part of the answer, add that information to the page first.

Copy linkDoes llms.txt improve Google Search visibility?

Google says Search ignores llms.txt when determining visibility and rankings, including in its generative AI features.[2]

To qualify as a supporting link in AI Overviews or AI Mode, a page must be indexed and eligible to appear with a search snippet, according to Google.[5]

Copy linkWhich tools actually use llms.txt?

Context7 processes the file when you submit its URL. Whether an assistant finds the file on its own depends on how it looks for information.[6]

Lighthouse flags server errors when it tries to fetch llms.txt. If the server returns a 404, Lighthouse marks the audit as "Not Applicable" because the file is optional.[7]

Copy linkHow llms.txt differs from a sitemap and robots.txt

What each file does
FilePurpose
llms.txtPoints AI tools to selected pages and describes what they cover.[1]
robots.txtSets crawl rules for bots that honour them.[9]
XML sitemapLists the URLs you want search engines to discover.[10]
llms-full.txtSome publishing platforms use this file to combine the text of several pages into one document.[8]

Check the documentation for each crawler before setting rules in robots.txt. Protect private pages with access controls.[9]

Copy linkHow to create an llms.txt file

Copy the template into a plain-text editor and replace the site name, headings and links with your own. Start with public pages that answer common questions about your site. Give each link a short description that explains what the page covers. Save the file as llms.txt.[1]

llms.txt starter template
# Website name

> Describe what the site covers.

## Topic

- [Page title](https://example.com/page): Say what this page explains.

Publish the file on your site

For a site-wide index, publish the file at /llms.txt on your domain. The original proposal allowed files in subdirectories, and version 2 defines their scope. For example, /docs/llms.txt covers pages under /docs/. When several files cover the same page, the one in the deepest directory on its path takes precedence.[3]

On WordPress, check whether a plugin you already use can publish an llms.txt file. If you have access to your site's files, you can upload your own file to the public folder for your domain using your hosting control panel's file manager or SFTP.[14]

If you deploy a site from a project, add llms.txt to the folder your build publishes as static files and redeploy. If you use a site builder, check whether its settings can generate the file or let you publish a text file at /llms.txt.

Open /llms.txt on your domain and check that it shows the text you published. Follow the links while signed out to make sure the pages are public. If you see your homepage or a 404, check where your platform published the file.

Copy linkCheck that tools can read the pages you list

If a visitor can see the answer in a browser but an assistant misses it, check what that assistant receives. Depending on the tool, it may read the HTML, inspect a screenshot or work from a description of the page's controls.[4]

Put the answer in visible text and keep structured data consistent with it. If a condition matters, such as when a policy takes effect, include it next to the detail it qualifies.[5][11]

Copy linkHow to test whether the file helps

Ask the same question in two fresh conversations with the same assistant. Give it your website address in both and the llms.txt link in the second. Keep the settings and website content the same so you can see what changes when you provide the file.

Check which pages the assistant opened and compare the answer with what those pages say. If your logs show a crawler request, use the provider's published guidance to verify its identity before drawing a conclusion.[12]

How to interpret a trial run
If you see thisWhat it tells you
The tool opened the index after you supplied the link.It could fetch the index in that run.
The tool found the index when you gave it only the website address.You observed automatic discovery in that run.
The tool opened the right pages and gave a correct answer.It found the information it needed for that question.

Repeat the comparison before relying on the result. Keep the file if it helps the tool reach the right pages and you can maintain the links. Measure search visibility or referral traffic separately if either is your goal.

Copy linkKeep the index current

Update the index when a linked page moves or its description stops matching the content. If your publishing platform generates the file, check it after changing how pages are organised.

Copy linkSources

  1. Jeremy Howard, "The /llms.txt file, v2". Originally published 3 September 2024. Revised on 10 August 2026.
  2. Google Search Central, "Optimizing your website for generative AI features on Google Search". See the section on llms.txt and other special markup. Page last updated 10 July 2026.
  3. llms-txt, "Changes". Version 2, August 2026.
  4. Kasper Kulikowski and Omkar More, "Build agent-friendly websites", web.dev. Last updated 1 April 2026.
  5. Google Search Central, "AI features and your website".
  6. Context7, "Add an llms.txt file". API documentation for explicit submission and processing.
  7. Chrome for Developers, "llms.txt", Lighthouse agentic-browsing audit. Last updated 5 May 2026.
  8. Mintlify, "llms.txt". Documentation for its generated indexes and combined exports.
  9. IETF, RFC 9309, "Robots Exclusion Protocol". September 2022. See sections 1 and 3 for the distinction between crawl rules and access authorisation.
  10. Google Search Central, "Learn about sitemaps".
  11. Google Search Central, "General structured data guidelines".
  12. Google Crawling Infrastructure, "Verify requests from Google crawlers and fetchers".
  13. Shopify, public llms.txt file
  14. WordPress Advanced Administration Handbook, "Updating WordPress using FTP". See the guidance on using a file manager or SFTP.

Further reading

  • Markdown reference from CommonMark
  • Creating helpful, reliable, people-first content
Doğu Abaris

About the author

Doğu Abaris

Doğu Abaris is a software and data engineer and a co-founder of Tityra. For more than a decade, he has built maintainable software for production, working across front-end and back-end development. He also contributes to open-source software and web standards.

More about Doğu
Share this article

Share this article

Keep exploring

Agent Experience

How AI agents interact with websites

AI agents can read pages, use browser controls or call tools directly, with each route shaping what they can see and do.

Read article

Content access

Why AI agents may miss website content

A page can look complete in a browser while another client misses its content or context. Compare responses to find where delivery or interpretation fails.

Audit practice

What is a content audit?

Learn how a content audit helps you decide what to change on your website, with a practical review process, an illustrative example and a checklist you can use.

Turn findings into
clear next steps.

Start for free
BlogAudit methodologyAPI docsMCP docsCLIGitHubContact

TITYRA LTD

120 Main Street
Largs, Scotland, KA30 8JN
info@tityra.com
HomeAbout
Who It's For
  • Publishers & Media
  • Ecommerce & Retail
  • SaaS & Technology
  • Agencies
  • Government & Public Sector
  • Financial Services & Insurance
PricingFAQ

© 2026 TITYRA LTD. All rights reserved. Registered in Scotland, company SC908253.

PrivacyTerms and ConditionsCookie informationCookie preferences

We value your privacy

By clicking "Accept all cookies", you agree to the storing of optional analytics cookies on your device to help us understand site usage and improve our website. You may click the customise button to choose which optional cookies you would like to allow.

Strictly necessary (2)

We save your cookie choice in this browser for six months, so you don't have to choose on every visit. This storage is always on.

Show detailsHide details for strictly necessary
  • Name
    tityra_analytics_consent_v1
    Provider
    Tityra (tityra.com)
    Type
    HTML local storage
    Maximum storage duration
    Persistent

    Remembers whether you accepted or rejected analytics. Your choice is valid for 180 days (six months), after which we ask again. The stored record remains until it is replaced or you clear your browser storage.

  • Name
    tityra_analytics_consent_v1_refusal
    Provider
    Tityra (tityra.com)
    Type
    HTML session storage
    Maximum storage duration
    Browser tab session

    Keeps analytics off if your browser can't save a rejection in local storage. This fallback is only used when needed and is cleared when a subsequent choice is successfully saved.

Google Analytics helps us understand page visits, content engagement, interest in audit packages and account signup link clicks. It only loads after you accept. Advertising features are disabled.

Show detailsHide details for analytics
  • Name
    _ga
    Provider
    Google Analytics (tityra.com)
    Type
    HTTP cookie
    Maximum storage duration
    Up to 180 days (six months)

    Distinguishes visitors to help us understand how the website is used. Set only after you accept analytics; advertising features are disabled.

  • Name
    _ga_*
    Provider
    Google Analytics (tityra.com)
    Type
    HTTP cookie
    Maximum storage duration
    Up to 180 days (six months)

    Maintains analytics session information, such as visits and interactions with the website. Set only after you accept analytics. The asterisk represents the identifier in the cookie name.

You control whether optional analytics runs on this website. We remember your choice for six months, and you can change it at any time using Cookie preferences in the footer.

Rejecting or withdrawing consent stops analytics and removes the Google Analytics cookies this website can access.

The details list the name, provider, purpose, type and storage duration of each entry. Contact details and private account information aren't included in website analytics.

Counts describe the entries listed, including the fallback and cookie name pattern, rather than cookies currently stored on your device.

Read our cookie information