Free llms.txt Generator and Checker

Generate an llms.txt file from your sitemap, or check the one you already have against the llmstxt.org spec. Includes an honest verdict on whether your site needs one at all.

What is llms.txt?

llms.txt is a proposed standard, published at llmstxt.org by Jeremy Howard of Answer.AI, for a markdown file at your site root that tells AI systems what your site contains. The idea is that language models work with limited context, so a curated map of your best content is more useful to them than a raw crawl.

The format is deliberately small. An H1 with your site name is the only required element. Most files then add a blockquote summary and a set of H2 sections, each holding a markdown list of links in name format with optional notes. A section titled "Optional" marks links that may be skipped when a shorter context is needed.

Being straight about its status: Google has said Search does not use it, no major AI lab has committed to reading it, and the largest studies find no citation lift. Measured bot behaviour is the clearest signal, with only 0.1% of AI bot visits fetching the file. What does read it today is documentation tooling and coding agents, which is why adoption clusters in developer docs. None of that makes it a waste of time. It costs minutes, adoption is growing quickly, and it is reasonable insurance against the standard hardening. It is simply not a citation tactic, and this tool will not pretend otherwise.

Results are estimates for informational purposes only. Not professional advice. We recommend verifying with a qualified expert.

Frequently Asked Questions

Does llms.txt help my Google rankings?+
No. Google's Gary Illyes confirmed in July 2025 that Google Search does not use llms.txt, neither for ranking nor for AI Overviews. SE Ranking's analysis of 300,000 domains found the file did not predict whether a site got cited, and their model actually performed better once the variable was removed. Anyone selling llms.txt as a ranking factor is overselling it.
Do ChatGPT, Claude or Perplexity read it?+
Not in any measurable way for AI search. OtterlyAI logged 62,100 AI bot visits across 90 days and only 84, or 0.1%, fetched llms.txt. None of the major labs have committed to consuming it, and their consumer sites do not serve one, though their developer documentation sites do. The reliable consumers today are documentation platforms and coding agents pointed at the file directly.
Then why create one at all?+
Four reasons that survive the evidence. It takes minutes and costs nothing. IDE agents such as Cursor, Claude Code and Copilot read it today, so if you publish docs it works right now. Adoption went from 1% to 5.6% of the top 10,000 sites in a year, so it is a cheap option on a standard that may harden. And choosing your ten most important pages is a useful exercise whether or not a model ever reads the result. What it will not do is lift your citations, so do not buy it on that basis.
What is the difference between llms.txt and llms-full.txt?+
llms.txt is a curated map: your site name, a summary and links to the pages that matter. llms-full.txt is your entire content in one file. Be careful with the full variant, because it gets large fast. Anthropic's is around 25MB, which is far heavier than the pages it is meant to save fetching. Most sites only need the first.
Is llms.txt the same as robots.txt?+
No, and the comparison flatters it. robots.txt controls access and crawlers honour it, partly because both sides want it to work. llms.txt describes content and nothing is obliged to read it. One is enforcement, the other is a suggestion, which is also why robots.txt becoming a standard is a weak precedent for llms.txt becoming one.
Does it reduce load on my server?+
Not today, despite the claim being common. Bots have to fetch the file for it to displace anything, and only 0.1% of AI bot visits do. A file nobody reads saves nothing. Where llms-full.txt is fetched it usually moves far more data than the pages it replaces, so the effect currently runs the other way.
What does this generator do about pages I have set to noindex?+
It leaves them out, and tells you how many it dropped. Most standalone generators skip this check and happily list pages you deliberately excluded from search. It also respects Disallow rules in your robots.txt.
Why did the generator leave out most of my pages?+
By design. The spec favours a curated file, and the common failure among generators is dumping an entire sitemap into markdown. We cap the list, keep the shallowest and highest-priority URLs, and report exactly what was left out so you can add anything important back.
Where do I put the file?+
At your site root, served as plain text at yourdomain.com/llms.txt. On most static hosts that means dropping it in your public folder. If you use Mintlify or GitBook it is generated for you, and on Shopify it already exists.

Want to know what actually gets you cited by AI?

llms.txt is a small piece. Our AI visibility checker tests bot access, citability, structured data and E-E-A-T across ChatGPT, Gemini and Perplexity.

Check your AI visibility

Learn more

← Back to Tools