AI search
llms.txt generator and checker
Generate an llms.txt file from your sitemap, using your pages' real titles and descriptions, or check the one you already have against the llms.txt proposal. No AI writing, and an honest word on what the file does.
Free · No signup · Reads public pages only
How it works
Enter your website and choose Generate or Check.
To generate, we read your sitemap, fetch up to 60 of your main pages for their titles and meta descriptions, and group them by section. To check, we read /llms.txt, compare it with the proposed format and test its links.
Edit the draft in the box, then copy or download it and upload it to the root of your site.
What llms.txt is
llms.txt is a plain-text file at the root of a site (example.com/llms.txt) that gives AI tools a short, readable map of your most useful pages. It was proposed in September 2024 by Jeremy Howard of Answer.AI and is written in Markdown, so people can read it too.
The proposed shape is simple: a # heading with your site or product name, an optional one-line > summary, a few lines of notes if you want them, then ## sections that list links as "- [Page name](https://...): what it covers". A section called ## Optional marks links a reader can skip when it's short on space. Some documentation sites also publish llms-full.txt, which puts the full text of their docs in one file.
Will it help you show up in AI answers?
Be realistic. llms.txt is a proposal, not a standard, and no major AI company has said it uses llms.txt to decide what to show or cite in search. ChatGPT search, Perplexity and Google's AI Overviews find pages through their own crawlers and indexes, the same way search engines always have.
Where it does get used is closer to home: coding assistants and agents that are pointed at a site's docs, and tools built to read it. That's why developer-tool companies were early to publish one.
So treat it as cheap insurance, not a ranking lever. It takes minutes to add, it can't hurt, and writing it is a useful exercise in deciding which pages actually explain what you do. If AI visibility is the goal, making sure AI crawlers can reach your pages, and that those pages answer questions clearly, matters far more.
How the generator builds your draft
It reads your sitemap (from robots.txt, /sitemap.xml or /sitemap_index.xml), or the links on your homepage if there's no sitemap. It favours shallow pages, your homepage and top-level pages first, and skips tag, category, author, search, login and cart pages. Then it fetches each page and uses its title and meta description, leaving out pages that error, redirect off-site or are set to noindex.
Pages are grouped by the first part of their address: /blog/... becomes a Blog section, /docs/... becomes Docs, and top-level pages sit under Pages. The site's name comes from the part of the title your pages share ("Pricing | Acme" gives "Acme"), and the summary from your homepage's meta description. Nothing is invented: if a page has no meta description, its link simply has no note.
Read the draft before you publish it. Cut pages that wouldn't help someone understand what you offer, put your most important pages first, and rewrite any description that's pure marketing. A short file of 10 to 30 strong links is easier for any reader to use than a dump of every URL.
What the checker looks at
- An H1 title at the top, and only one.
- A > summary under the title.
- ## sections, each with links in the "- [name](url): notes" form.
- Links that are full https:// addresses and actually load (we test up to 20).
- The file served as plain text, not as a web page, which is what a single-page app often returns for any unknown address.
It can't tell you whether any AI tool reads your file. Your server logs can: look for requests to /llms.txt and which user agents make them.
Questions people ask
Does Google use llms.txt?
Google hasn't said it uses llms.txt for Search or AI Overviews. Google's AI features rely on Googlebot and the normal search index, so robots.txt, crawlable pages and clear content are what count there.
Where do I put the file?
At the root of your site, so it loads at https://yoursite.com/llms.txt, served as plain text. On most hosts that means putting it in the public or static folder, next to robots.txt.
Is llms.txt the same as robots.txt?
No. robots.txt tells crawlers what they may fetch. llms.txt doesn't allow or block anything; it's a reading list that points AI tools to your most useful pages.
Does the generator use AI to write the descriptions?
No. Every title and description comes from your own pages. If a description is missing or weak, the fix belongs on the page too, because the same text appears in Google's results.
Is this llms.txt generator free?
Yes. No signup. It reads your public sitemap and pages, and the draft stays in your browser for you to edit.
Want it done for you?
Romeo makes your pages worth listing
An llms.txt is only as good as the pages it points to. Romeo rewrites the titles and descriptions that say nothing, makes your key pages easy for AI answers to quote, and keeps the file current. You approve every change.
