Free tool · llms.txt generator

llms.txt generator: build the file in minutes

Fill in your site name, a one-line summary and the pages that matter, and this llms.txt generator writes the Markdown file for you, in the format set out at llmstxt.org. Copy it or download it, then upload it to your site root as /llms.txt. It is free, runs in your browser and works offline.

Describe your site

Becomes the H1. It is the only part the proposal requires.
One or two plain sentences: what you are, who it is for. Becomes the > blockquote.
Paragraphs or a list. No headings here; lines that start with # are removed.

Sections and links

Each section becomes an H2 with a list of links. Add a short note to each link so a reader knows what it will find.

Your draft is kept in this browser only.

Your llms.txt

Add your site name to start.

Checks

    The format

    What goes in an llms.txt file?

    An llms.txt file is a Markdown file at /llms.txt that gives AI tools a short map of your site. It starts with an H1 name, then an optional one-line summary in a blockquote, optional detail, and H2 sections that list links in the form - [Title](URL): note. Only the H1 is required.

    Part, in orderMarkdownRequired?What to write
    Name# Site nameYesYour brand or project name, as people search for it
    Summary> One or two sentencesNoWhat you are, who it is for, the one fact that matters most
    DetailParagraphs or lists, no headingsNoContext to read before the links: markets, limits, terms
    File lists## Section then - [Title](URL): noteNoYour key pages, grouped. The note after the colon is optional
    Optional## OptionalNoSecondary links a tool can skip when it needs a shorter context

    Source: llmstxt.org, the proposal by Jeremy Howard, first published 3 September 2024. The page now calls itself v2, last modified 10 August 2026 (checked 7 Nov 2026). It also suggests a clean Markdown copy of each page at the same URL with .md added. This generator builds the index file only.

    Honest status

    Which AI tools actually read llms.txt?

    Nobody can give a full list, because llms.txt is a proposal, not a standard that AI companies sign up to. What we could confirm: Google says Google Search ignores it, Chrome's Lighthouse checks the file, and coding agents can load it when someone points them at a site. No major AI search product we checked says its crawler reads it.

    WhoWhat they say (checked 7 Nov 2026)
    Google SearchIts AI optimisation guide (updated 10 Jul 2026) says you do not need AI text files or Markdown to appear in Search, Google Search ignores them, and it is fine to create them for other services.
    Chrome LighthouseThe agentic browsing audit flags a server error when the file is requested. A missing file (404) is marked not applicable, because the file is optional for now.
    OpenAI, Anthropic, PerplexityTheir crawler pages (OpenAI, Anthropic, Perplexity) talk about robots.txt only. None of them says the crawler reads llms.txt.
    llmstxt.orgSays thousands of sites publish one, and that OpenAI, Anthropic and Google publish llms.txt files for their developer docs. Publishing a file is not the same as reading other sites' files.
    Our view: publish one, because it takes 20 minutes and costs nothing. Do not expect it to lift rankings or AI citations by itself. The work that gets you cited is still crawlable pages, clear answers and mentions on other sites. We keep our own file at /llms.txt and update it whenever we publish a page.

    How we write them

    5 rules for a useful llms.txt

    Treat llms.txt as a short briefing note, not a second sitemap. List the pages that answer buyer questions, write each note as a plain fact, and keep secondary links in the Optional section. A focused file of 20 to 40 links is easier for a tool to use than a dump of every URL.

    1. Lead with buyer pages. Pricing, product or service pages, comparisons, case studies and contact come first. Old news posts and tag pages do not belong here.
    2. Write notes as facts, not slogans. "Plans, limits and what each tier includes" helps a reader. "World-class solutions for modern teams" tells it nothing, and a tool may quote your note word for word.
    3. Put the facts you want repeated in the summary. If AI answers often get your market or offer wrong, state the correct fact in the blockquote, in one sentence.
    4. Check robots.txt next. llms.txt does not grant access. If robots.txt blocks a bot, the file does not change that. Test it with our AI crawler checker.
    5. Make it part of publishing. Add a step to your page checklist: new page live, then sitemap and llms.txt updated. A stale file that points to deleted pages is worse than a short one.

    Common questions

    llms.txt Generator: FAQs

    An llms.txt file is a plain Markdown file at the root of your website, at /llms.txt, that gives AI tools a short, curated map of your site. It holds your name, a one-line summary and lists of your key pages with a short note on each. It was proposed by Jeremy Howard in September 2024 and is not an official web standard.
    No, not for Search. Google's AI optimisation guide (updated 10 July 2026) says Google Search ignores AI text files such as llms.txt, and you do not need one to appear in Search or its AI features. Google says it is fine to create one for other services. Chrome's Lighthouse does check whether the file loads without a server error.
    No. robots.txt tells bots what they may crawl, and sitemap.xml lists every URL for search engines. llms.txt is a short, hand-picked guide for AI tools and does not grant or block access. If robots.txt blocks a bot, an llms.txt file does not change that. Keep all three.
    Put it at the root of your domain so it loads at https://yoursite.com/llms.txt, the same place as robots.txt. On WordPress, Webflow or Netlify that usually means adding a file to the site root or using an SEO plugin that supports it. Open the URL in a browser afterwards to check it shows as plain text.
    Links that are useful but not essential, such as a changelog, older guides or long reference pages. The proposal says tools can skip the Optional section when they need a shorter context, so put the pages you most want read in the sections above it.
    Your draft is saved only in this browser, using local storage, so it is still there when you come back. Nothing is sent to SignalScaler. Clear all removes the fields; clearing your browser's site data removes the saved draft.

    Related

    Related tools and guides

    AI search visibility

    Want AI tools to get you right?

    We check what ChatGPT, Perplexity and Google AI say about you, then fix the pages, files and mentions behind it.

    We reply within one business day.

    We use cookies to understand how visitors use this site. Analytics cookies stay off unless you say yes — see our Cookie Policy for details.

    Cookie Preferences

    Strictly Necessary
    Required for the site to function. Always on, cannot be disabled.
    Analytics
    Helps us understand how visitors use the site (Google Analytics). Off by default.