Skip to content
RankX AI

Cookie settings

Choose which cookies we can use. You can change this at any time from “Cookie settings” in the footer.

Essential

Security, bot protection and remembering your choice. The site needs them to run, and they do not identify you. Always on.

Google Analytics cookies that tell us which pages are read and which links are followed, so we can improve them. Off until you switch it on.

Tells advertisers when their advert led to your visit. Includes the Meta (Facebook) pixel and the LinkedIn Insight Tag, which set cookies on this domain (LinkedIn also on linkedin.com) and can be told if you later start a trial.

More in the cookie policy and the privacy policy.

The llms.txt Generator writes a spec-valid file, not a dump.

An llms.txt generator writes the llms.txt file for your website: a short markdown list of your key pages for AI agents and LLM tools. RankX AI reads your sitemap, picks the pages that matter, writes their notes from your own metadata and validates the file against the specification.

Free, with no account. We read your sitemap and up to 60 pages, one request at a time, honouring your robots.txt, and cache results for 24 hours.

Example resultSample data
halewick.example · 3 links · 38 pages readSpec valid

llms.txt · serve at /llms.txt

# Halewick Supply

> Made-to-measure replacement kitchen doors, cut to size and shipped across the UK.

## Products

- [Shaker doors](https://halewick.example/shaker): Painted and oak fronts
- [Pricing](https://halewick.example/pricing): Prices by size and finish

## Help

- [Measuring guide](https://halewick.example/measure): Measure an old door

For online stores

Selling online? Build it from your catalogue.

A store’s most useful pages are its collections, its best sellers and its policies, not whatever its sitemap lists first. Enter a Shopify or WooCommerce store and the file is built from those, then checked against the spec.

Reads the store’s public collections or categories, its best-selling products and its policy pages. Free, no account, nothing stored.

Already have one? Check your llms.txt

Reads the file at yoursite.com/llms.txt and checks it against the llmstxt.org format: one H1, the summary, sections and link lists.

Definition

What is llms.txt, and who needs an llms.txt file?

llms.txt is a proposed markdown file at your site root that lists your most useful pages, with a short note each, for AI agents and large language models to read. Think of it like a reading list: robots.txt says what a crawler may fetch, sitemap.xml lists every URL, and llms.txt points to the pages worth reading first.

  • What it is

    A short reading list, written in markdown

    An llms.txt file names your site in one H1, sums it up in a blockquote, then lists your key pages under H2 headings, each a link with an optional note. Agents read it on demand to find the right page, and the format is a community proposal in its second version.

    It points AI systems at pages; it changes nothing about what a crawler may fetch.

  • Who it is for

    Documentation sites first, everyone else optionally

    The proposal's own author says llms.txt files are used most heavily for software documentation, where coding agents follow them to API references and tutorials. Stores and marketing sites publish one as a clean, cheap map of their best pages.

    Being cited by ChatGPT or Google is decided by crawler access and the page itself.

  • What it costs to run

    A free llms.txt generator, with no account

    The llms.txt Generator is free and needs no account: enter your website URL and it generates an llms.txt file in about a minute. A run considers up to 100 sitemap URLs, fetches at most 60 pages while honouring your robots.txt, keeps about 50 links and caches the file for 24 hours.

    No sitemap means a file built from the homepage alone, and a thinner one.

How it works

How does the llms.txt generator work?

Generate llms.txt in about a minute: the generator reads your site, curates the links and checks the file before you see it.

  1. Enter your URL to generate the file

    Type your domain and press generate. A Shopify or WooCommerce store can build the file from its catalogue in the store band above instead.

  2. Read the sitemap, politely

    The generator finds your sitemap through robots.txt or the usual path, considers up to 100 of its URLs and fetches at most 60 pages, one request at a time. It honours your robots.txt, and with no sitemap it works from your homepage alone.

  3. Curate about fifty links

    Pages are grouped into sections, ranked, and cut to about 50 links, with commercial pages first, the blog last and the overflow under Optional. Each note is your own meta description.

  4. Validate, then publish

    A built-in llms.txt validator checks the file against the specification before you see it. Edit it, then host it at your domain root as /llms.txt.

What this generates

What does a valid llms.txt file look like?

A valid llms.txt file is small and ordered: one required H1, a short structure and lists of links. The llms.txt Generator follows that published grammar and validates its output.

The grammar LLM tools expect, in five rules

  1. 1. One H1 naming the site. It is the only required element in the whole format.
  2. 2. An optional blockquote directly after it, carrying a short summary a model should read first.
  3. 3. Optional prose next: paragraphs or lists, with no headings of any level.
  4. 4. H2 sections last, each a markdown list whose entries are a link, name and URL, with an optional colon and note.
  5. 5. An H2 named Optional, by convention, holds secondary links an agent can skip. Since v2 it is a convention only, with no mechanical meaning.

Files can also live at subpaths such as /docs/llms.txt, and version 2 of the proposal, published in August 2026, says a file covers the pages under its path. It also adds a way for a page to point at the file that covers it: a link with rel="describedby".

Mechanically it is a plain text file, like robots.txt, and it is not a sitemap.xml replacement. A sitemap lists every URL for traditional search engines to crawl, while llms.txt hands AI models a short curated reading order with none of your navigation, cookie banners or footer around it. That is the appeal to anyone building on assistants like ChatGPT, Claude or Gemini, and the reason to curate the file rather than dump a URL list.

An llms.txt example, as the generator writes it

llms.txtExample
# Harbour Joinery

> Harbour Joinery designs, makes and fits bespoke kitchens and fitted furniture across Bristol and Bath.

Generated by the RankX AI llms.txt Generator on 2026-10-01 from harbourjoinery.test's sitemap. Curated to the most important pages; edit freely before publishing at /llms.txt.

## Key pages

- [About us](https://harbourjoinery.test/about): A workshop of six joiners in Bristol, making kitchens and furniture since 2009.
- [Contact](https://harbourjoinery.test/contact): Book a home visit or ask for a written quote.

## Services

- [Bespoke kitchens](https://harbourjoinery.test/services/bespoke-kitchens): Hand-made kitchens in oak, walnut and painted finishes, designed and fitted in eight to twelve weeks.
- [Fitted wardrobes](https://harbourjoinery.test/services/fitted-wardrobes): Built-in wardrobes and alcove units made to measure for older houses.

## Pricing

- [What a kitchen costs](https://harbourjoinery.test/pricing): Typical project ranges, the deposit and what every quote includes.

## Blog

- [How long does a bespoke kitchen take?](https://harbourjoinery.test/blog/kitchen-timeline): The design, making and fitting stages, week by week.

## Optional

- [Careers](https://harbourjoinery.test/careers)
- [Privacy policy](https://harbourjoinery.test/privacy)

A fictional business on a reserved .test domain. Grammar per llmstxt.org, v2, August 2026, verified 1 October 2026.

What the evidence shows

Does an llms.txt file help AI SEO?

An llms.txt file is a reading aid for AI agents, not a ranking signal. Here is what the published measurements show, so you can decide what to expect from it.

What the request logs show

Ahrefs studied 137,210 domains in 2026: about 28% publish an llms.txt, and 97% of those files got no requests at all in May 2026. Of the requests that did arrive, the largest share, about 22%, came from SEO audit tools, and AI retrieval bots made 1.1%. Publish it as tidy housekeeping, and measure AI traffic with the tools that track it.

What Google says about it

Google's guide to generative AI features, last updated 10 July 2026, says you do not need AI text files to appear in Google Search or its AI Overviews, because Google Search itself does not use them. OpenAI, Anthropic and Google publish llms.txt files for their own developer documentation, and none documents reading yours.

The fabricated directive to avoid

A claim circulates that Anthropic honours a Commercial-Use directive inside llms.txt, but it appears in no version of the specification and no vendor documentation. To control training use of your content, robots.txt tokens are the documented mechanism, and the AI Crawler Access Checker tests them.

Publishing it

How do I add llms.txt to my website?

Serve the file at your domain root, then treat it like content. Three habits keep it worth publishing.

Put it at /llms.txt

Host it at your domain root as a plain text file, beside robots.txt. A documentation section can carry a second file at /docs/llms.txt, which covers the pages under that path, and the most specific file wins.

Edit before you publish

The generator ranks pages by sitemap structure and depth, a good first guess. You know which ten pages explain your business best, so promote them, cut the rest and keep the file under about 50 links.

Update it when pages change

A stale index points agents at the wrong pages, so update your llms.txt file when key pages change. Keep it in version control with your site and regenerate after significant content changes; a repeat run inside a day returns the cached result instantly.

llms.txt beside robots.txt and sitemap.xml

llms.txt compared with robots.txt and sitemap.xml
robots.txtsitemap.xmlllms.txt
Its jobSays which paths a crawler may fetchLists every URL you want indexedPoints agents at your best pages, with notes
FormatPlain text rules per user agentXML, one entry per URLMarkdown: an H1, a summary, lists of links
StatusInternet standard, RFC 9309Sitemaps protocol, read by Google and BingCommunity proposal, v2 since August 2026
Who reads itSearch and AI crawlers, before they fetchSearch engine crawlersCoding agents and LLM tools, on demand; no AI search engine documents it
Where it lives/robots.txt, one per hostAny URL, declared in robots.txt/llms.txt, or a subpath it then covers

Keep going

Free AI SEO tools for what decides AI visibility

AI visibility is decided by crawler access, page mechanics and what AI answers cite. Each has a tool here.

What decides whether an assistant can read you

Two things, and llms.txt is neither: whether an AI assistant's crawler is let in at all, which the AI Crawler Access Checker tests for every documented bot, and whether your words are in the HTML without JavaScript, which the AI Readiness Score measures page by page.

In RankX AI, the daily site signal watch re-reads your llms.txt, your robots.txt and your homepage every day and scores the llms.txt it finds, and on WordPress the RankX AI WordPress integration can serve an llms.txt from your site's root without a file on disk.

Questions

llms.txt generator questions, answered

Direct answers, with the evidence behind each one.

What is an llms.txt generator?

An llms.txt generator is a tool that writes llms.txt, the proposed markdown file at a website’s root that lists its most useful pages for large language models and AI agents. The RankX AI llms.txt Generator reads your sitemap, keeps about fifty pages, writes each note from your own meta descriptions and checks the finished file against the spec.

Is the llms.txt generator free to use?

Yes. It is free, needs no account and asks for no email: enter your website URL and you get a ready-to-use llms.txt file in about a minute. A repeat run within 24 hours returns the cached file instantly.

Where did llms.txt come from, and what is in the file?

llms.txt was proposed by Jeremy Howard of Answer.AI in September 2024 and revised as version 2 in August 2026. The file holds one H1 with the site name, the only required element, then an optional blockquote summary, optional prose and H2 sections of markdown links with notes. The longer story is in what llms.txt is, and whether you need one.

Does llms.txt actually work?

It works as a reading list for documentation, where coding agents follow it to the right page. For search visibility, no published evidence shows an effect: Ahrefs found in 2026 that 97% of llms.txt files received no requests in May, and AI retrieval bots made 1.1% of the requests that did arrive. Treat it as cheap housekeeping, and put the effort for AI search into crawler access and the pages themselves.

Does Google use llms.txt?

No. Google’s guide to generative AI features in Search, last updated 10 July 2026, says you do not need AI text files to appear in Google Search, including its generative AI features, because Google Search itself does not use them. An llms.txt file neither helps nor harms Google rankings or Google AI Overviews.

Why use an llms.txt generator?

Because a correct file takes care to write by hand, and tools that generate llms.txt files do it in a minute. More than a quarter of the domains Ahrefs studied publish the file, documentation platforms build one automatically, and it doubles as a clean map of your best pages. The RankX AI generator curates the pages and validates the result, so the file you publish follows the spec.

What makes an llms.txt file valid?

A valid file has exactly one H1 naming the site, then, in order, an optional blockquote summary, optional prose with no headings, and H2 sections holding markdown lists of links. Each entry is a name and URL, optionally followed by a colon and a note, with no H3s anywhere. A built-in llms.txt validator checks the generator’s own output against those rules before handing it to you.

Does the Optional section still matter?

Less than it did. An H2 named Optional marks secondary links an agent can skip, and the llms.txt Generator puts its overflow there. Version 2 of the proposal, published in August 2026, keeps Optional as a convention but removes its mechanical meaning.

How do I create a full llms.txt file?

A full file usually means llms-full.txt, a documentation-platform convention that concatenates every documentation page into one markdown file; the llms.txt specification never mentions it. Platforms such as Mintlify and Fumadocs build it automatically, or you can export each page as markdown and join them in order. It suits docs sites rather than stores, so this tool generates llms.txt only.

Is there a Commercial-Use directive for llms.txt?

No. The claim that Anthropic honours a Commercial-Use directive inside llms.txt appears in no version of the specification and in no vendor documentation, and it traces back to a single SEO blog post that cites no source. To control training use of your content, robots.txt tokens are the documented mechanism.

Why does the generator cap the file at around 50 links?

Because curation is the point of the format: an llms.txt that mirrors your whole sitemap is just a worse sitemap. The specification asks for a file small enough to fit in an agent’s context, with the detail behind the links. The generator keeps roughly the best fifty pages, orders sections commercial pages first and blog last, and writes each note from the page’s own meta description.

How does the generator build the file?

It reads your sitemap, or finds it through robots.txt, considers up to 100 of its URLs and fetches at most 60 pages, one request at a time, while honouring your robots.txt. It extracts each page’s title and meta description, groups and ranks the pages, and writes a spec-valid file with your homepage’s description as the summary. With no sitemap it falls back to your homepage alone.

How do I add llms.txt to my website?

Serve it at the root of your site as /llms.txt, next to robots.txt, as plain text or markdown. A file at a subpath such as /docs/llms.txt covers the pages under that path, and agents should use the most specific file. On Shopify, a theme template named llms.txt.liquid serves your own file, and on WordPress the RankX AI plugin can serve it from the root.

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

robots.txt says what crawlers may fetch and is an internet standard, RFC 9309. sitemap.xml lists every URL you want search engines to index, and llms.txt points AI agents at your best pages first, as a proposal that enforces nothing. The AI Crawler Access Checker tests the first; this generator writes the third.

Can you show an example of an llms.txt file?

Yes, the page above carries a full one. The smallest valid llms.txt is a single H1 such as "# Example Site"; a useful one adds a blockquote summary, then H2 sections such as "## Services" listing pages as a name in square brackets, a URL in round brackets and a short note. It ends with an "## Optional" section for pages an agent can skip.

How often should I update my llms.txt file?

Update your llms.txt file whenever the pages it lists change: a new collection, a retired product, a moved URL. Keep it in version control with the site and regenerate after significant content changes. In RankX AI, the daily site signal watch re-reads the file and records when it disappears or its quality score drops.

Start here

See where you show up in AI answers today.

Start with your website. RankX AI recognises your platform, suggests the questions to track and audits your pages, with first results minutes after setup.

7-day free trial. No credit card required. On Shopify, install the app and Shopify bills your plan.