Free llms.txt Generator

Generate a free llms.txt file online in 30 seconds. Tells ChatGPT, Claude, Perplexity, Cursor, and Google AI Overviews which pages on your site matter most. Works for WordPress, Shopify, Next.js, Webflow, and plain HTML. No signup. No card.

1. Tell us about your site

Three quick fields. Tap the eye to see what each one means.

2. Add your important pages

Group your main pages — Docs, Pricing, Blog, anything that matters.

  • For each page: what it's called, where it lives, and a quick line about it.

3. Your file

# Your site

## Docs

- [Getting started](/docs/getting-started): A quick guide for first-time users.

## Other

- [What's new](/changelog): Latest product updates.

Save this as llms.txt and upload it to the root of your site, so it lives at yoursite.com/llms.txt.

What is llms.txt?

llms.txt (sometimes written llms-txt or llms txt) is a small markdown text file you put at the root of your website. It tells large language models — ChatGPT, Claude, Perplexity, Cursor, Google's AI Overviews, Apple Intelligence — which pages on your site are authoritative and worth citing.

Think of it as a hand-picked map of your most important pages, written in a format LLMs can read in one pass. When someone asks an AI tool a question about your topic, the AI reads your llms.txt to figure out which of your URLs to cite inside its answer. More AI citations = more visitors who already trust you.

The format was proposed in late 2024 by Jeremy Howard (Answer.AI) and is now adopted by Anthropic, Stripe, Cloudflare, Hugging Face, and a growing list of tech-forward sites. It's the robots.txt of the AI-search era.

How to use this llms.txt generator

  1. 1. Tell us about your site. Name, web address, and one sentence describing what your site is. This sentence becomes the blockquote at the top of your llms.txt file — the first thing every AI reads.
  2. 2. Add your important pages. Group them by type — Docs, Pricing, Features, Blog, Changelog — and list the pages AI tools should know about. Each page gets a title, a URL (full or relative), and an optional one-line description.
  3. 3. Copy or download.You'll get a valid llms.txt file in proper markdown format — ready to upload.
  4. 4. Upload it to your site. Put it at the root of your domain (the same place as robots.txt and sitemap.xml). Then open yoursite.com/llms.txt in a browser to verify it loads as plain text.

llms.txt examples

Two real-world llms.txt patterns — one for a SaaS product, one for a documentation-heavy site. Both follow the official spec: H1 for the site name, blockquote for the one-line description, H2 sections grouping links, bulleted markdown links with optional descriptions.

Example 1 — SaaS product
# Acme Invoicing

> Acme is the simplest way for freelancers to send invoices and get paid online.

## Product

- [Pricing](https://acme.com/pricing): Plans start at $9/month for unlimited invoices.
- [Features](https://acme.com/features): Recurring invoices, ACH, Stripe, Apple Pay.
- [Integrations](https://acme.com/integrations): QuickBooks, Xero, FreshBooks.

## Help

- [Getting started](https://acme.com/help/getting-started): Send your first invoice in under 60 seconds.
- [Connecting your bank](https://acme.com/help/connect-bank): How to receive payments via ACH or Stripe.
- [Tax reporting](https://acme.com/help/taxes): Year-end 1099 export, by country.

## Optional

- [Changelog](https://acme.com/changelog): Recent product updates.
- [Status](https://status.acme.com): Live system status and uptime history.
Example 2 — Documentation site
# Stripe API

> Stripe builds payment infrastructure for online businesses, from one-off charges to subscription billing and global payouts.

## API reference

- [Authentication](https://stripe.com/docs/api/authentication): How to authenticate API requests with a secret key.
- [Charges](https://stripe.com/docs/api/charges): Create, retrieve, and refund charges.
- [Customers](https://stripe.com/docs/api/customers): Manage customer objects and saved payment methods.
- [Subscriptions](https://stripe.com/docs/api/subscriptions): Recurring billing endpoints.

## Guides

- [Quickstart](https://stripe.com/docs/quickstart): Process your first payment in five minutes.
- [Webhooks](https://stripe.com/docs/webhooks): React to Stripe events in real time.
- [Going live](https://stripe.com/docs/live-mode): Pre-flight checklist before switching from test to live keys.

## Optional

- [Changelog](https://stripe.com/docs/changelog): API version history.

llms.txt best practices

Five rules from real-world llms.txt files that get cited well in AI answers.

Frequently asked questions

What is an llms.txt file?

It’s a small markdown text file you put at the root of your website (yoursite.com/llms.txt) that tells AI tools — ChatGPT, Claude, Perplexity, Cursor, Google’s AI Overviews — which of your pages are authoritative and worth citing. It was proposed by Jeremy Howard at Answer.AI in late 2024 and is now used by Anthropic, Stripe, Cloudflare, Hugging Face, and a growing number of tech sites.

Why do I need an llms.txt file?

AI tools answer more and more questions every day. Without llms.txt, they guess which of your pages are important — and often pick the wrong ones. With llms.txt you tell them directly. Your pages get cited more often inside ChatGPT, Claude, and Perplexity answers, which sends you visitors who already trust you.

What does an llms.txt file look like (format)?

It’s plain markdown. H1 with your site name, blockquote with a one-line description, then H2 section headings each containing a bulleted list of markdown links with optional one-line descriptions. The official spec is at llmstxt.org. See the examples on this page for two complete files you can copy-paste.

Where exactly do I put the llms.txt file?

At the root of your domain — the same place as robots.txt and sitemap.xml. The full address should be https://yoursite.com/llms.txt. It must load as plain text and be open to everyone (no login). Subdomains (like blog.yoursite.com) need their own llms.txt.

How do I add llms.txt to WordPress, Shopify, or Next.js?

WordPress: upload the file to the root of your hosting via FTP or SFTP, alongside wp-config.php. Shopify: use a custom theme file or an app like SEO Manager that lets you add files at the root. Next.js: drop llms.txt into the /public folder and it serves at yoursite.com/llms.txt automatically. Webflow and Squarespace: use a redirect or custom code injection — both have docs covering robots.txt that apply to llms.txt the same way.

What’s the difference between llms.txt and llms-full.txt?

llms.txt is the curated index — a short, hand-picked list of your most important pages. llms-full.txt is the optional companion file that includes the actual content of those pages in one big markdown file, so AI tools can ingest your full site in a single fetch. Most sites should ship llms.txt first, then add llms-full.txt once that’s working.

What’s the difference between llms.txt, robots.txt, and sitemap.xml?

All three live at the root of your domain but do different jobs. robots.txt tells web crawlers which paths to skip. sitemap.xml is the complete list of every page on your site so search engines can index them. llms.txt is a hand-picked list of your most important pages, written for AI tools to cite. They complement each other — most sites should have all three.

How do I check or validate my llms.txt file?

Open https://yoursite.com/llms.txt in a browser. It should load as plain text (not HTML, not JSON) and look like the markdown examples on this page. For deeper validation, you can use the llmstxt.org reference page to compare against the spec, or paste your file into ChatGPT or Claude and ask 'is this a valid llms.txt file' — both can verify the format.

Do I still need llms.txt if my SEO is good?

Yes. Good SEO helps you rank on Google’s blue-link results. llms.txt helps you get cited inside AI answers — that’s GEO (Generative Engine Optimization) and AEO (Answer Engine Optimization), separate visibility surfaces. Even sites that rank #1 on Google can be invisible inside ChatGPT and Perplexity if their content isn’t structured for LLM consumption.

You'll also want