.png){kind=small}
llms.txt is a proposed text file, placed at a website's root, that lists a site's most important pages in a format intended to help AI systems find and understand a site's content more efficiently. It's modeled loosely on robots.txt, but it isn't an official web standard, and as of 2026 no major AI company (OpenAI, Google, Anthropic, Meta) has publicly committed to reading or acting on it in production.
What is llms.txt?
A markdown file at your site's root that summarizes what your site is and links to your most important pages, intended as a navigation aid for AI systems rather than a ranking or blocking mechanism.
Is llms.txt an official standard?
No. It's a community proposal with no backing from a recognized standards body. Adoption is voluntary and inconsistent across AI providers, which is why results vary so widely.
Do AI bots actually read llms.txt right now?
Rarely, and this is worth being direct about. Independent studies tracking hundreds of millions of AI crawler visits have found llms.txt fetch rates well under 1% of total AI bot traffic, and Google's own team has said on the record that Google doesn't use it and isn't planning to. Some providers do fetch it occasionally, but "occasionally" is the honest word.
How many URLs should I include?
Your genuinely important pages, product, pricing, documentation, key content hubs, not a dump of your entire sitemap. A curated 20 to 30 link file is more useful than an exhaustive one, both for any system that does read it and as a forcing exercise for your own content priorities.
Does llms.txt affect Google rankings?
No. Google has confirmed no Search system reads or acts on it, comparing it to the long-discredited keywords meta tag.
How is llms.txt different from robots.txt or a sitemap?
Robots.txt controls crawler access and is widely respected, including by AI-bot-specific user agents like GPTBot and ClaudeBot, which is currently the lever that actually shapes AI crawler behavior. A sitemap is a technical index for search engines. llms.txt is neither, it's a curated summary aimed at AI systems specifically, with no enforcement mechanism behind it.
How do I add llms.txt on my website?
Create a plain markdown file named llms.txt, place it at your root domain, and structure it with a short site summary followed by linked sections for your key pages. It's a low-effort addition, usually half a day of work, so the honest case for doing it is optionality and low cost, not a guaranteed visibility gain.
How to create the llms.txt file?
Start with a one-paragraph description of your site, then group your most important URLs into a few clear sections (product, documentation, key content), linking to markdown versions of pages where available rather than the HTML URLs.
How do I verify AI bots are reading my llms.txt?
Check your server logs for requests to /llms.txt specifically. Given how rarely major crawlers currently request the file, don't be surprised if you see very little activity, that's consistent with what independent research is finding industry-wide, not a sign something's broken on your end.
