Skip to content

LLMs.txt Generator

Create a standards-compliant llms.txt file so AI engines understand your site

LLMs.txt Generator — How It Works

The llms.txt standard is a simple text file — placed at your domain root — that tells large language models what your site is about, what pages exist, and how they relate to each other. Think of it as robots.txt for AI: robots.txt controls what crawlers can access; llms.txt explains what they'll find once they get there.

Why llms.txt matters for AEO

AI engines like ChatGPT, Claude, Perplexity, and Google AI Overviews increasingly cite external sources in their answers. But unlike traditional search engines, these models don't crawl and index pages the same way. They need clear, structured signals about what a site offers.

An llms.txt file gives AI models a machine-readable map of your site — titles, URLs, and one-line descriptions — so they can quickly understand what you publish and cite it accurately. Sites without llms.txt rely entirely on the model's training data, which may be outdated or incomplete.

The llms.txt format

The format follows a simple Markdown-like structure proposed by Jeremy Howard in late 2024. It starts with a site name as a heading, a blockquote description, then sections listing pages as Markdown links with optional descriptions.

The file lives at /llms.txt on your domain root (e.g. https://example.com/llms.txt). Some sites also offer an /llms-full.txt with complete page content for models that accept larger context windows.

What to include

Focus on your most important pages — not every URL on the site. Include your homepage, key product or service pages, cornerstone blog posts, documentation, and any page you'd want an AI to cite when answering questions in your niche. Leave out login pages, admin panels, duplicate content, and thin pages.

Each entry should have a clear, descriptive title and a one-sentence summary. Avoid marketing language — AI models prefer factual, descriptive text they can quote directly.

How this generator works

Enter your site name, URL, and a brief description. Then list your pages — one per line, separated by pipes: Title | URL | Description. The tool formats everything into a valid llms.txt file you can copy or download and place at your domain root.

The output follows the current llms.txt specification: heading, blockquote description, and a flat list of Markdown-formatted links with descriptions.

$ faq

What is llms.txt? ▸
llms.txt is a text file placed at your website's root (e.g. example.com/llms.txt) that provides AI language models with a structured overview of your site. It lists your key pages with titles, URLs, and descriptions so AI engines can understand and cite your content accurately.
Do ChatGPT and Claude actually read llms.txt? ▸
Several AI platforms and their web crawlers have started recognizing llms.txt as a signal. Perplexity, Claude (via ClaudeBot), and various AI search tools actively look for it. Even when not directly consumed, having a well-structured llms.txt improves how AI training pipelines process your site.
How is llms.txt different from robots.txt? ▸
robots.txt controls access — it tells crawlers which pages they can or cannot visit. llms.txt provides context — it explains what your site is about and what each page covers. They serve complementary purposes and both should exist on an AI-optimized site.
How many pages should I list in llms.txt? ▸
List your 10-50 most important pages. The file should be a curated overview, not a full sitemap. Focus on pages you want AI engines to cite: cornerstone content, key product pages, documentation, and authoritative articles. Thin or duplicate pages don't belong here.
Where do I put the generated file? ▸
Upload it to your domain root so it's accessible at yourdomain.com/llms.txt. Most web hosts allow you to place files in the public root directory (public_html, www, or htdocs). If you use a CMS, you may need to configure routing to serve the file directly.
Should I also create llms-full.txt? ▸
llms-full.txt is an optional companion that includes the full text content of each listed page. It's useful for AI models with large context windows that can process entire articles at once. Start with llms.txt — if you see AI citation traction, consider adding the full version.