Validate an existing llms.txt against the spec, or generate one for your site in a minute.
llms.txt is a proposed standard (similar to robots.txt, but for AI assistants) that tells LLMs which pages on your site are most useful for context, which to skip, and what your site is about. It lives at /llms.txt on your root domain and is written in simple Markdown.
AI assistants like Claude, ChatGPT, and Perplexity can read llms.txt to get a structured overview of your content — especially useful for sites with deep documentation, large blogs, or multiple product areas.
Validator mode: paste a URL or raw llms.txt content and the tool checks it against the spec — required H1 title, optional blockquote summary, correct section structure, and valid Markdown link formatting.
Generator mode: fill in your site name, description, and the most important pages — the tool outputs a spec-compliant llms.txt file you can upload directly.
Docs-heavy sites, SaaS products, personal sites with deep content archives, and anyone who wants more control over how AI assistants summarize and cite their work. It’s a low-effort signal that helps LLMs navigate your content without crawling everything.
No. robots.txt controls which crawlers may access your pages. llms.txt curates and describes your best content for AI assistants. They solve different problems and can sit side by side.
It makes your content easier for AI assistants to parse and cite. Adoption is early, so treat it as a low-cost signal rather than a guaranteed ranking factor.
At the root of your domain, served at /llms.txt, the same level as robots.txt.
Related tools: AI crawler access checker and robots.txt validator and generator. Background reading: AEO vs SEO.