BUY WEBSITES
BUY DOMAINS
LOGIN
SIGNUP
llms.txt Generator
An llms.txt file is a small Markdown-formatted file placed at a site’s root that points AI assistants and large language models to the pages a site owner most wants them to read, such as documentation, product pages, and key guides. This llms.txt generator assembles that file from a site name, a one-line summary, and grouped sections of labelled links, producing the exact # title, > summary, and ## section structure the convention expects.
The tool is free and runs entirely in your browser. Nothing typed into it is uploaded or stored, the output updates as you edit, and you can copy the result or download it as llms.txt ready to upload to your domain root.
# Title at the top of the file.
> blockquote under the title.
🔒 Private: everything runs in your browser. Nothing you paste is uploaded.
Place the saved file at the root of your domain so its URL is
https://yourdomain.com/llms.txt. llms.txt is an emerging, non-binding convention —
no major AI assistant is guaranteed to read or honour it, so treat it as a hint, not a directive.
How to build and use an llms.txt file
Fill in the site name and summary, group your most important URLs into sections, and the file assembles live. Copy or download it, then upload it to the root of your domain.
Lead with a clear title and a single-sentence summary
The file opens with one # heading carrying the site name, followed by a > blockquote that summarises the site in a single sentence. Treat that summary the way you would a meta description: it is the first context an AI assistant reads, so it should state plainly what the site is and who it serves. An optional free-form paragraph can follow with extra detail. Keep both tight and factual, because a model skimming the file will lean on these lines to decide which of the linked pages are worth fetching for a given question.
Group links into sections that mirror reading priority
Below the summary, each ## heading starts a section, and every link beneath it follows the - [label](url): note pattern. Convention reserves a section titled Optional for links a model can safely skip when it is short on context, so put documentation, product, and pricing pages in named sections and lower-priority material under Optional. Write labels a human would recognise and use the note to say in a few words what each page covers, which gives the assistant enough signal to choose the right URL without guessing from the slug.
Place the file at the root and treat it as a hint
Save the output as llms.txt and upload it so it resolves at https://yourdomain.com/llms.txt, the same root-level convention as robots.txt. Because the format is plain Markdown, you can edit it by hand later or regenerate it here when your key pages change. The convention is still emerging and non-binding: no major AI assistant is contractually required to read or obey it, so it is a way to express preference and surface your best content, not a guaranteed control over how any model uses your site.
llms.txt generator frequently asked questions
Q1What is an llms.txt file and where does it go?
An llms.txt file is a Markdown file that lists the pages a site owner most wants AI assistants to read, organised under a title, a one-line summary, and labelled sections of links. It belongs at the root of your domain, so its address is the site origin followed by the filename, the same placement convention used by robots.txt and sitemaps.
Q2Is llms.txt an official standard that AI assistants must follow?
No. It is an emerging, community-driven convention, not a ratified standard, and no major AI assistant is required to read or honour it. Treat it as a way to express a preference and surface your best content. Whether any given model fetches the file or weighs its hints is entirely up to that model’s operator.
Q3How is llms.txt different from robots.txt?
robots.txt tells crawlers which paths they may or may not access and is widely respected by search engines. llms.txt does the opposite in spirit: it positively points AI assistants toward the content you most want them to use, written in human-readable Markdown rather than crawler directives. They solve different problems and can sit side by side at your domain root.
Q4Does this generator send my links or content anywhere?
No. The entire file is assembled in your browser with client-side JavaScript. The site name, summary, and links you enter are never uploaded, logged, or stored on any server, and the copy and download actions work on the text the page built locally. You can use it for unpublished or private sites without anything leaving your machine.
Q5What should I put in the Optional section?
The Optional section is a convention for links an assistant can skip when it has limited context, so reserve it for lower-priority material such as changelogs, archives, or secondary guides. Keep your most important pages, like core documentation, product pages, and pricing, in clearly named primary sections so a model reading top to bottom encounters them first.
