TL;DR: llms.txt is a proposed Markdown file at a site’s root that gives AI tools a short, curated list of important pages. It is optional and unofficial. Google says no special AI files are needed to appear in AI Overviews, and Google’s John Mueller has said no AI system currently uses it. Treat it as low-cost documentation, not an SEO tactic.
Last reviewed: 15 October 2026
Every few months a new file or tag is sold as the secret to AI search visibility. The current favourite is llms.txt. Before you spend time on it, you should know what it is, what evidence exists, and what to do first.
This guide explains the proposal, what Google and other sources have said, who might benefit, and the steps that reliably improve visibility in AI answers. It is written by Janak Pokharel, an SEO practitioner and co-founder of Limi Creatives, with the view that AEO and GEO start with the same foundations as ordinary SEO.
What is llms.txt?
llms.txt is a proposed convention for a Markdown file at the root of a website that gives large language models a concise, curated entry point to the site. It was proposed by Jeremy Howard and published on 3 September 2024. It is not an official web standard.
The llms.txt proposal sets out a simple format. The file starts with an H1 containing the site or project name, which is the only required part. A blockquote gives a short summary. H2 sections then contain lists of links in the form of a name, a link and optional notes. By convention, an Optional section holds secondary links that an agent can skip when it needs less context. The stated goal is to point agents to clean, concise pages instead of making them work through navigation and clutter.
You can create a correctly formatted file with the free llms.txt generator.
Does Google use llms.txt?
No evidence shows that Google uses llms.txt. Google’s documentation says no special files, markup or optimisation are needed to appear in AI Overviews or AI Mode, and John Mueller said on Bluesky in June 2025 that no AI system currently uses llms.txt.
Google’s page on AI features and your website states: “You don’t need to create new machine readable files, AI text files, or markup to appear in these features.” The same page says a page must be indexed and eligible to be shown with a snippet, and that standard SEO practices still apply. Search Engine Roundtable reported Mueller’s comment in Google: No AI System Currently Uses LLMs.txt. Other platforms may behave differently, and the situation can change, so check current statements from each AI provider before you rely on any of this.
| Claim | Evidence | Verdict |
|---|---|---|
| llms.txt improves Google rankings | Google lists no such requirement or ranking use | Unsupported |
| llms.txt is needed for AI Overviews | Google says no special AI files are needed | Not required |
| Any AI system reads llms.txt | Mueller said none currently does, June 2025 | Unconfirmed |
| It costs little to publish | It is a small Markdown file | True |
Who might still benefit from llms.txt?
Documentation sites, developer tools and software help centres may benefit most, because people use AI coding assistants to read and apply technical docs. A curated index can help such tools find the right page. For a typical small business site, the benefit is uncertain.
The proposal itself was written with this use in mind: agents that need concise, expert information in one accessible place. If your audience includes developers who ask AI assistants about your product, publishing a clear index of your docs is reasonable. For a shop, a local service business or a personal blog, there is no evidence that it changes how often you are mentioned.
If you do publish one, keep it short, factual and current. Remove links that redirect or fail, and update descriptions when pages change purpose. It should list roughly the ten to thirty pages that matter most, not every URL. A complete URL list is the job of your XML sitemap.
What actually improves visibility in AI answers?
The same fundamentals that help in search: pages that can be crawled and indexed, clear and accurate content, consistent facts, trustworthy sources and structured data that matches the page. Allow the search crawlers you want, answer questions directly and publish information other sites do not have.
Google’s AI features guidance lists practical steps, and they match good SEO:
- Allow crawling in robots.txt and through your CDN or host. Decide deliberately which AI crawlers to allow, using the robots.txt generator.
- Make content easy to find with clear internal links.
- Keep important content in text rather than only in images or scripts.
- Make structured data match the visible text. The schema markup generator helps you build valid markup.
- Verify your site in Search Console to diagnose issues.
Beyond these basics, answer engines favour pages that state facts clearly, name entities explicitly and support claims with sources. Write short, self-contained answers under question headings, as this article does. Read the full AI SEO guide for a practical checklist.
Should you create an llms.txt file?
Create one only if you can do it in under an hour and you maintain documentation that AI tools may read. Do not treat it as a growth tactic, and do not skip crawling, content quality or structured data to make time for it.
- Fix the foundations first. Run the free SEO audit and resolve crawling, indexing and content issues.
- Decide if it is useful. Documentation and developer sites have the best case.
- Generate and upload. Place it at the root of the domain.
- Maintain it. Review it whenever you add or retire an important page.
For planning AI search visibility alongside your wider strategy, see the advanced SEO service page.
Conclusion
llms.txt is a small, optional proposal with no confirmed effect on Google rankings or AI citations. Google says no special files are needed, and Mueller said in June 2025 that no AI system uses it. Build one if it suits your documentation, but put your effort into crawlable, accurate, well sourced content first. If you want a clear plan for AI search visibility, Limi Creatives offers a free SEO audit that you can request through the contact page.
Frequently asked questions
Is llms.txt an official standard?
No. It is a proposal published by Jeremy Howard in September 2024. It has no official standard status, and search engines and AI providers decide for themselves whether to use it.
Will llms.txt help me rank in Google?
There is no evidence that it will. Google’s documentation says no special AI files or markup are needed to appear in its AI features, and it does not list llms.txt as a ranking factor.
Where do I put the llms.txt file?
The proposal places it at the root of the site, for example at the top level of your domain, or at a subpath where it covers the URLs beneath it.
What is the difference between llms.txt and robots.txt?
Robots.txt tells crawlers which URLs they may access. llms.txt is a curated reading list in Markdown for language models. They do different jobs, and one does not replace the other.
How can I get cited by AI answer engines?
Make sure your pages are crawlable and indexed, answer questions directly, keep facts consistent, cite sources, add accurate structured data and publish original information that other pages lack.
Who is behind this tool
Nomor AI Marketing is a free tool made by two companies that work side by side. One builds the software and the other does the marketing, so a finding in your report can go to the people who fix it.
Nomor
Our software development company. Nomor designs and builds the software and websites behind this tool, including the audit engine, the PDF report and the pages you are reading. It is the right place to start for custom development, performance work and technical fixes.
Limi Creatives
Our marketing company. Limi Creatives is a creative agency that runs SEO, paid ads, content, social media and video for brands. It is the right place to start when you want help turning audit findings into traffic and enquiries.