FREE TOOL
llms.txt Generator
Import your sitemap. Edit with live preview. Export a valid llms.txt.
Help AI tools and agents find the pages that matter on your site. No account, and the editor never leaves your browser.
Paste a site URL or sitemap.xml to pre-fill the sections, or build by hand below.
# Acme Docs > Acme is a hosted API for sending transactional email. This file helps AI tools find the docs that matter. Start with the Quickstart, then the API reference. The Optional section can be skipped for a shorter context window. ## Docs - [Quickstart](https://acme.com/docs/quickstart): Send your first email in five minutes. - [API reference](https://acme.com/docs/api): Every endpoint, parameter, and response. - [Authentication](https://acme.com/docs/auth): API keys and OAuth. ## Optional - [Changelog](https://acme.com/changelog): Release history. - [Status](https://status.acme.com): Live uptime.
llms.txt at the root of your site (https://yoursite.com/llms.txt).Paste your sitemap.xml URL and the generator pulls in your pages, groups them into sections, and fills in titles automatically.
Produces a valid llms.txt: H1 title, summary blockquote, and grouped link lists with the special Optional section.
The whole document lives in the URL. Send the link, or export a clean llms.txt to drop at the root of your site.
The editor runs in your browser. Sitemap import only fetches the public pages you point it at — nothing is stored.
What goes in an llms.txt
The name of your site or project. It is the one required element of the spec.
One line telling an AI tool what your site is, so it can decide what to read.
H2 sections (Docs, API, Guides) holding the pages worth reading, each with a short note.
A trailing section whose links can be skipped first when context is tight.
Already have a file? Run it through the llms.txt validator to check it against the spec.
Frequently asked questions
llms.txt is a plain-text file you place at the root of your website (yoursite.com/llms.txt) that tells AI tools and agents which pages matter and how to read them. It uses Markdown: an H1 with your site name, a blockquote summary, and H2 sections containing curated link lists. Think of it as a sitemap written for large language models instead of crawlers.
At the root of your domain, served at https://yoursite.com/llms.txt as text/plain. Many teams also publish an llms-full.txt with the full content inlined, but the curated link list in llms.txt is the place to start.
Paste your sitemap.xml URL (or your site root and we'll try /sitemap.xml). We read the listed pages, group them by URL path into sections, and fetch a capped number of pages to pull in their titles and descriptions. You then edit everything before exporting. Large sitemaps are capped and clearly flagged.
Yes. No sign up, no limits, no watermarks. The output is plain text you can commit and host anywhere.
The editor itself is entirely client-side. The only network call is the optional sitemap import, which fetches the public pages at the URL you provide and returns the parsed structure — it is not stored.
Treat it like any other file in your repo: commit it, and update it when your documentation structure changes. Moxie Docs keeps the documentation behind these links current automatically on every merge, so the pages your llms.txt points to stay accurate.
Your llms.txt is only as good as the docs behind it
Moxie Docs connects to your GitHub repositories, generates searchable documentation, catches drift on every merge, and serves that context to AI coding agents over MCP. The pages your llms.txt points to stay current without manual upkeep.
No credit card required to start. Cancel anytime.