What is an llms.txt file?

An llms.txt file is a Markdown file at the root of a website that points language models to the pages that matter most. Jeremy Howard proposed it on September 3, 2024 (the proposal was last updated on August 10, 2026). It is a proposal, not a formal standard, and no major AI search engine says it uses the file for ranking.

By the Brisano team Updated November 18, 2026 4 min read

An llms.txt file is a plain Markdown file that sits at /llms.txt on your domain and tells language models, in a few lines, what your site is and which pages to read first. The proposal on llmstxt.org was published by Jeremy Howard on September 3, 2024 and last modified on August 10, 2026. If you already have one, check your llms.txt file against the format before you go further.

Is llms.txt a standard?

Not in the formal sense. The llms.txt standard is a public proposal: no standards body such as the W3C or the IETF has adopted it, and the text can change (it did in August 2026). What it has is adoption by tools. On November 18, 2026, llmstxt.org listed Mintlify, GitBook, Yoast SEO, AIOSEO and Wix among the platforms that generate the file, plus plugins for VitePress, Docusaurus and Drupal.

The large AI search engines haven't signed up to it. Google says you "don't need to create new machine readable files, AI text files, or markup" to appear in AI Overviews or AI Mode (Google Search Central), and OpenAI's crawler documentation doesn't mention llms.txt.

The llms.txt format, section by section

The file is Markdown, and the sections come in a fixed order (llmstxt.org):

  1. An optional byte-order mark (BOM).
  2. An H1 with the name of the project or site. This is the only required section.
  3. A blockquote with a short summary of the site.
  4. Optional paragraphs or lists with more detail, without headings.
  5. H2 sections that each hold a list of links, written as [name](url): notes.
  6. An optional section called Optional, for links an agent can skip when it needs a shorter context.

Markdown versions of your pages

The proposal also suggests a clean Markdown copy of useful pages: the same URL with .md added (page.html.md) or with the extension replaced (page.md); URLs without a file name use index.html.md or index.md. A page can point to its Markdown copy with rel="alternate" type="text/markdown", as an HTML <link> or an HTTP Link: header (llmstxt.org).

What about llms-full.txt?

llms-full.txt is a convention some tools use for one file with the full text of a site's key pages. The llms.txt proposal doesn't define it (checked on November 18, 2026), so it is optional. The free checker reports whether your site has one.

An annotated llms.txt file

# Brightlane

> Brightlane is invoicing software for freelancers who bill monthly retainers.

Brightlane works in 30 currencies. Prices are in USD.

## Product

- [Features](https://brightlane.com/features): retainers, late-payment reminders, multi-currency
- [Pricing](https://brightlane.com/pricing): plans and limits

## Docs

- [Getting started](https://brightlane.com/docs/start.md): set up your first retainer

## Optional

- [Changelog](https://brightlane.com/changelog)

The H1 names the product, the blockquote says what it does and for whom, the paragraph adds one fact, each H2 groups links with a short note, and "Optional" holds what an agent can skip. For llms.txt examples from real websites, see the llms.txt examples directory.

Check an llms.txt Enter a domain: we fetch its llms.txt and validate it.

How to create and publish an llms.txt file

  1. List the 10 to 30 pages a newcomer should read: product, pricing, docs, policies.
  2. Write a one-sentence summary that states what you do and for whom.
  3. Group the links under a few H2 headings and add a short note to each link.
  4. Save the file as UTF-8 and publish it at the root of your domain.
  5. Validate it, then keep it in sync when pages move.

The llms.txt file generator drafts the file from your site. On WordPress, Yoast SEO and AIOSEO can generate it (both are listed on llmstxt.org).

llms.txt for online stores

An online store has thousands of URLs; the llms.txt file should not list them all. Link the main category pages, the shipping, returns and warranty policies, size guides, the brands you carry and the contact page. Add a note to each link with the facts a buyer asks about (delivery times, return window). Keep product feeds and the sitemap for the full catalogue.

llms.txt best practices

  • Absolute URLs for every link.
  • Only indexable, reachable pages: nothing blocked by robots.txt or behind a login.
  • Short notes after each link that say what the page answers.
  • UTF-8, and the file served as plain text at the root.
  • Update it when pages move or prices change, and validate after each change.

Does llms.txt help SEO or get you into AI answers?

There is no evidence that it does. llms.txt does not block or allow crawlers: that is robots.txt. It doesn't list every URL: that is your sitemap. And it is not a signal any major engine says it uses: Google says no AI text files are needed for its AI features, as quoted above. Getting "indexed by an LLM" through llms.txt isn't a documented mechanism.

That makes llms.txt a low-cost courtesy to tools and agents that choose to read it. Add it if it takes you an hour; don't expect it to change how often AI engines mention you. To know whether anything changes, track the same prompts before and after with an AI visibility tracker. Before that, make sure AI crawlers can reach your pages at all: the AI crawler checker and the guide on what GPTBot is cover it.

llms.txt vs robots.txt vs sitemap.xml

File Purpose Who reads it
robots.txt Allow or block crawling Search and AI crawlers that honour it
sitemap.xml List every URL you want indexed Search engines
llms.txt Curated guide to your key pages Tools and agents that choose to read it

Sources

  1. The /llms.txt file · llmstxt.org (Jeremy Howard), checked 2026-11-18
  2. AI features and your website · Google Search Central, checked 2026-11-18
  3. Overview of OpenAI crawlers · OpenAI, checked 2026-11-18

Frequently asked questions

Is llms.txt a standard?

Not a formal one. It is a public proposal on llmstxt.org, first published on September 3, 2024 and last updated on August 10, 2026. No standards body such as the W3C or the IETF has adopted it, although several platforms generate the file.

Where does the llms.txt file go?

At the root of the site, so it loads at https://example.com/llms.txt, the same way robots.txt does.

What is the only required part of llms.txt?

An H1 heading with the name of the project or site. The proposal lists everything else, the summary blockquote, the detail paragraphs and the link sections, as optional.

Does llms.txt get my site into ChatGPT or other LLMs?

There is no evidence that it does. No major AI search engine has said it uses llms.txt to choose which sites to mention or cite. To be found by ChatGPT search, your pages must be reachable by OAI-SearchBot.

Do OpenAI or Google use llms.txt?

Google says you don't need new machine-readable files or AI text files to appear in AI Overviews or AI Mode. OpenAI's crawler documentation does not mention llms.txt (checked on November 18, 2026).

Does llms.txt replace robots.txt or a sitemap?

No. robots.txt controls crawling and a sitemap lists URLs for search engines. llms.txt is a curated, human-readable guide to your most useful pages.

What is llms-full.txt?

A convention some tools use for a single file with the full text of a site's key pages. It is not defined in the llms.txt proposal, so treat it as optional.

See where you stand in AI answers.

Choose a plan and see your first answers in minutes.