Skip to content

llms.txt Generator

Fill in a few fields and get a valid llms.txt file that tells ChatGPT, Perplexity, and other AI systems what your site is and which pages matter. Already have one? Check an existing file against the llmstxt.org format. Free, no signup, built entirely in your browser.

What is llms.txt?

llms.txt is a markdown file at your site root that gives AI crawlers a curated summary of your website: what it is, who runs it, and annotated links to the pages that matter most. It is the AI-search counterpart to robots.txt and sitemap.xml.

New to the format? Read the full guide: What is llms.txt?

1. Your site

Your llms.txt

Fill in the name, a summary of 30+ characters, and at least one section with one complete link to enable copy and download.


                    

Upload the file to your web root so it is reachable at yoursite.com/llms.txt. See a live example at jnabear.com/llms.txt.

What the llms.txt validator checks

The rules come from the format section of llmstxt.org (opens in a new tab), checked on 2026-09-29. Errors break the format, warnings are worth fixing, and notes explain a convention.

  • No H1, or more than one. The file opens with one H1 naming the site or project, which llmstxt.org calls "the only required section". Only a byte-order mark may come before it.
  • A heading other than H2. After the H1 and its summary, the only headings allowed are H2s, and each one starts a section of links.
  • A list item that is not a link. Each item in an H2 section is a markdown link, [name](url), optionally followed by a colon and notes.
  • No blockquote summary. A short > summary belongs right after the H1. It is optional, but it is what tells a reader what the site is.
  • Relative URLs. The format does not require absolute URLs, but a relative one cannot be resolved once the file is copied away from your site.
  • Empty sections, or prose inside a section. An H2 with no links says nothing, and text between the links may be skipped by a parser.
  • The Optional section. By convention, an H2 named "Optional" holds secondary information: "links an agent can skip when a shorter context is needed." Keep your key pages out of it.

Will anything read a valid llms.txt?

Not Google Search. Google's guide to its generative AI features (opens in a new tab) says that maintaining llms.txt files "will neither harm nor help your site's visibility or rankings in Google Search, as Google Search ignores them."

Outside Google, most files go unread. In a June 2026 study (opens in a new tab), Ahrefs checked the 137,210 domains in Ahrefs Web Analytics, found about 38,000 with a valid llms.txt, and reported from their server logs that "97% of those files received zero traffic in May 2026." Ahrefs counted a file as valid when it returned real Markdown rather than an error page; it "did not explicitly study whether a file was well-formed against the llms.txt specification," which is the part this validator checks. It also notes that its customers "skew more technical and SEO-aware than the web at large," and calls every figure in the study "a ceiling on actual llms.txt consumption."

So a clean result here means the file is well-formed. It is not a promise that any AI system will fetch, read, or cite it.

Sources

llms.txt: frequently asked questions

llms.txt is a plain-markdown file at your site root (yoursite.com/llms.txt) that gives AI systems a curated summary of what your site is and links to its most important pages. It follows the llmstxt.org convention: an H1 with the site name, a blockquote summary, and sections of annotated links.

No. Google's guidance for its AI features says "You don't need to create new machine readable files, AI text files, or markup to appear in these features." Some other AI tools and agents do read llms.txt, so it can still be worth adding as low-cost insurance, but not as a Google tactic.

Upload it to your web root so it is reachable at https://yoursite.com/llms.txt, the same place as robots.txt. On WordPress, most SEO or file-manager plugins can place it; on a static host, drop it in the public folder.

No. robots.txt controls whether crawlers may access pages. llms.txt describes your site to AI systems that already have access: what it is, who runs it, and which pages best represent it. They complement each other.

Paste it into the "Check an existing file" tab on this page. The validator tests it against the llmstxt.org format: exactly one H1 with the site or project name, which is the only required part; no headings other than H2 after it; and file-list items written as [name](url), optionally followed by a colon and notes. It also warns about a missing blockquote summary, relative URLs, and sections with no links. It checks structure only: whether an AI system fetches the file is a separate question.

Disclaimer

This free tool generates a file following the llmstxt.org convention and checks an existing file against the same format, as published on llmstxt.org and checked on 2026-09-29. The checker reports structure only; it cannot see whether anything fetches your file. llms.txt is an emerging convention, not a ratified web standard: some AI systems read it, and Google says Google Search ignores it. Adding one cannot hurt and takes minutes, but it is not a guarantee that any AI system will read, honor, or cite your site. Everything you type or paste stays in your browser; nothing is uploaded or stored. The generated file is yours to use however you like.

Want your whole site optimized for AI search?

llms.txt is one small signal. Entity-mapped content, schema, and topical authority are the big ones. Start with a free teardown of your top 3 gaps.

I reply within 24 hours, personally.