llms.txt Generator
Build an llms.txt file that gives AI assistants a short map of your site: what it is, and which pages to read. Fill in the form, then copy or download the file.
One or two factual sentences: what it is, who it's for, what makes it different.
Plain text under the summary: pricing, audience, contact.
Sections with no complete links (title and URL) are left out. Name a section "Optional" for pages an assistant can skip when it's short on space.
llms.txt
# Your site name
Upload it to your site root so it loads at https://yoursite.com/llms.txt, served as plain text.
Format check
- No "> summary" blockquote under the title. It's the line agents read first.
- No "## " sections. Group your key pages under H2 headings.
Already published? Validate your live llms.txt.
The llms.txt format, with an example
# Acme
> Acme is an invoicing app for freelancers: send invoices, track payments and chase late clients automatically.
Free plan for up to 5 clients; Pro is $12/month. Works in 30 currencies.
## Core pages
- [Pricing](https://acme.com/pricing): Plans, limits and what each includes
- [Features](https://acme.com/features): Invoicing, payment reminders and reports
- [Acme vs FreshBooks](https://acme.com/vs/freshbooks): Feature and price comparison
## Docs
- [Getting started](https://acme.com/docs/start): Create an account and send a first invoice
- [Stripe integration](https://acme.com/docs/stripe): Accept card payments on invoices
## Optional
- [Changelog](https://acme.com/changelog): Release notes
- [Terms](https://acme.com/terms): Terms of serviceWhat to include, and what to leave out
- Include the pages that answer the questions people ask about you: pricing, features, how it works, comparisons with alternatives, getting-started docs, and your best guides.
- Add key facts under the summary: price range, who it's for, platforms, founding year, contact. An assistant can quote them without opening another page.
- Put legal pages, changelogs and archives in the Optional section.
- Leave out login, account, checkout and search pages, tag archives, and anything blocked in robots.txt.
- Use absolute URLs (https://...), so the file still works when it's pasted into a chat.
How to add llms.txt to your site
| Platform | Where the file goes |
|---|---|
| Next.js | Put llms.txt in the public/ folder, or add app/llms.txt/route.ts to build it from your data (example below). |
| Astro, Vite, Gatsby, Hugo, Jekyll | Put it in the folder copied to the site root as-is: public/ or static/ in most setups. |
| Netlify, Vercel, Cloudflare Pages | Same as your framework: anything in the build's output root is served at /llms.txt. |
| WordPress | Upload it to the web root, the folder that holds wp-config.php, with your host's file manager or SFTP. Some SEO plugins can generate one too. |
| Express or another Node server | Serve it as a static file, or add a route that sends it with Content-Type: text/plain. |
| Shopify, Wix, Squarespace | Hosted builders usually don't give you direct access to the site root. Check your platform's help docs or app store for llms.txt support. |
// app/llms.txt/route.ts — build llms.txt from data so it never goes stale
export const revalidate = 86400; // rebuild once a day
export async function GET() {
const posts = await getTopPosts(20); // your own data function
const body = [
"# Acme",
"",
"> Acme is an invoicing app for freelancers.",
"",
"## Guides",
"",
...posts.map((p) => `- [${p.title}](https://acme.com/blog/${p.slug}): ${p.summary}`),
].join("\n");
return new Response(body, {
headers: { "Content-Type": "text/plain; charset=utf-8" },
});
}llms.txt, robots.txt and sitemap.xml compared
| File | What it holds | Who reads it |
|---|---|---|
| robots.txt | Which crawlers may fetch which paths | Every crawler, before it fetches anything |
| sitemap.xml | Every public URL, for discovery | Search engine crawlers |
| llms.txt | A short, curated map: what the site is and its most useful pages | AI assistants and agents that need context fast |
| llms-full.txt | The full text of your key pages in one file | Agents that want everything in one request |
llms.txt: common questions
What is llms.txt?
llms.txt is a plain-text Markdown file at the root of a website (yoursite.com/llms.txt) that gives AI assistants a short summary of the site and a list of its most useful pages. It was proposed at llmstxt.org in 2024.
Do ChatGPT and Google use llms.txt?
No AI company has confirmed that its search crawler uses llms.txt for ranking or citations. It is used by AI coding tools and agents that fetch documentation, and it costs little to publish. Treat it as a helpful map, not a ranking factor.
Where do I put the file?
At the root of your domain, so it loads at https://yoursite.com/llms.txt, served as plain text (text/plain or text/markdown). In most frameworks that means the public or static folder.
How many links should llms.txt have?
Enough to cover what people ask about you, usually 10 to 50. It's a curated map, not a sitemap: pick the pages that answer questions, and put everything else in your sitemap.
What's the difference between llms.txt and llms-full.txt?
llms.txt is a short map: a summary plus links. llms-full.txt is an optional companion that contains the full text of your key pages in one file, so an assistant can read everything in a single request.
What goes in the Optional section?
Pages an assistant can skip when it's short on context, such as legal pages, changelogs or older posts. The llms.txt format gives a section named Optional that meaning.
How often should I update it?
Whenever your pricing, product or key pages change. If your site has a blog or product catalog, build the file from your data (like the Next.js route above) so new pages appear automatically.