llms.txt Generator
Build a valid llms.txt that tells AI assistants which pages on your site matter. Everything is assembled in your browser.
How to use it
- Enter your site name and a one-line summary. The summary becomes the blockquote at the top, which is the first thing an assistant reads.
- Add a short about paragraph if the summary is not enough on its own.
- List your key pages, one per line, as
Title | URL | note. The note is optional but helps an assistant pick the right link. - Put lower-priority links under optional pages - these go in an "Optional" section that assistants are allowed to skip.
- Copy the result or download it, then upload it to the root of your domain so it lives at
/llms.txt.
What it does, and what it does not
It does: build a clean, correctly structured llms.txt in the format the proposal describes - an H1 name, a blockquote summary, optional prose, then Markdown link lists grouped into "Key pages" and "Optional". It updates live as you type and lets you download the file with the right name.
It does not: crawl your site to discover pages for you, or check that the URLs you enter are live. You decide what belongs in the file - that curation is the whole point of llms.txt. It also does not upload anything: the file is assembled in your browser.
Reference
llms.txt is a proposed standard for a plain-text, Markdown file at the root of your domain that tells large language models which pages matter and what your site is about. Think of it as a curated table of contents written for machines rather than a crawler that has to guess. It does not replace your XML sitemap or your robots.txt; it sits alongside them and answers a different question - not "what exists" but "what is worth reading".
The format is deliberately simple. The file starts with a single H1 that names the site. Directly under it, an optional blockquote gives a one or two sentence summary. After that you can add a few short paragraphs of context, then one or more H2 sections, each containing a Markdown list of links in the form - [Title](https://url): optional note. A section named "Optional" has special meaning: it flags links that an assistant can skip if it is short on context. This tool follows that structure exactly.
Where should you point the links? Lead with the pages that best explain what you do and drive your business - core service or product pages, your most useful guides, and key documentation. Keep the notes short and factual; they are hints, not marketing copy. If you maintain long-form documentation, some sites also publish an llms-full.txt with the full text inlined, which is why this tool offers that filename toggle.
A few honest caveats. llms.txt is still an emerging convention - not every AI system reads it yet, and adoption is uneven. Publishing one will not, on its own, get you cited in AI answers. What it does is remove ambiguity for the systems that do support it, and it costs you a few minutes. Given how cheap it is to add, it is worth having, especially if you have already invested in strong content that you want represented accurately. Keep it updated when your important pages change, the same way you would a sitemap.
Questions
Where do I put the llms.txt file?
At the root of your domain, so it is reachable at https://yourdomain.com/llms.txt. Upload it the same way you would a robots.txt file.
Is llms.txt an official standard?
It is a proposed, community-driven convention rather than an official standard from any search engine. Support is growing but not universal. It is low-effort to add, which is the main argument for doing it.
What is the difference between llms.txt and llms-full.txt?
llms.txt is a concise index of links. llms-full.txt is a larger file that inlines the actual content of your key pages so a model has the full text in one place. Use the checkbox to name your download accordingly.
Will this get my site cited by ChatGPT or Claude?
Not by itself. It helps systems that read the file understand your site, but citations depend on far more - content quality, authority and whether the model was trained on or can retrieve your pages. Treat it as a small, cheap improvement, not a growth hack.
Do the URLs get checked?
No. The tool formats whatever you enter without fetching anything. Double-check that your URLs are correct and live before you publish the file.