llms.txt is a plain Markdown file at the root of your site that lists your most important pages for AI tools, but there is no confirmed evidence it improves citations: Google's John Mueller has called it "purely speculative for now" and said no AI platform has asked sites to provide one. If you still want one, it takes about ten minutes to create and costs nothing.
What is llms.txt?
llms.txt is a proposal from Jeremy Howard of Answer.AI, published in 2024. The file sits at yourdomain.com/llms.txt and gives language models a curated, Markdown summary of your site: a title, a short description, and links to key pages with one-line notes.
It is different from robots.txt, which controls what crawlers may access, and from a sitemap, which lists URLs for search engines. llms.txt is meant to help a model understand what matters, not to grant or deny access.
Does llms.txt actually work?
As of now, there is no official confirmation that major AI search products use it. Mueller has said AI services have not claimed to use the file and compared it to the old keywords meta tag. Google's own documentation on AI features says you do not need "new machine readable files, AI text files, or markup" to appear in AI Overviews or AI Mode.
The honest summary: it is a low-cost, low-evidence bet. Documentation sites sometimes publish one so a developer can point a coding assistant at it, which is the use case where it has the clearest value. For a blog, treat it as optional.
How to create an llms.txt file
Use this structure, per the llmstxt.org proposal:
- An H1 with your site or project name
- A blockquote with a one-to-two sentence summary
- Optional paragraphs with context
- H2 sections containing bulleted links, each with a page title, its URL and a short note
Keep it to your 10 to 30 best pages. Describe each in plain words, because the point is clarity for a model that has never seen your site. Do not paste whole articles into it.
How to publish it on Next.js
On a static site, drop the file in the public folder. On a Next.js site with a CMS, a Route Handler at app/llms.txt/route.ts can generate the list from your latest posts and return it with a text/plain content type, so the file never goes stale. That is how acemo.io serves its own llms.txt.
After deploying, open yourdomain.com/llms.txt in a browser and confirm it returns plain text, not an HTML page.
When llms.txt is worth it
Add it if you publish developer or product documentation, where people may point a coding assistant at it, or if you can generate it automatically at no extra effort. Skip hand-maintaining one for a marketing blog and put the time into answer-first content and clean technical SEO instead, as covered in our guide to getting cited by AI search engines.
Related reading: is FAQ schema still worth it in 2026 and SEO vs GEO vs AEO.
Frequently Asked Questions
What is an llms.txt file?
llms.txt is a Markdown file placed at the root of a website that gives language models a curated list of the site's most important pages with short descriptions. It was proposed in 2024 by Jeremy Howard and is documented at llmstxt.org.
Does Google use llms.txt?
No. Google's documentation on AI features says you do not need new machine-readable files or AI text files to appear in AI Overviews or AI Mode, and John Mueller has described llms.txt as speculative. It has no confirmed effect on Google rankings or AI citations.
Is llms.txt the same as robots.txt?
No. robots.txt tells crawlers which URLs they may or may not access, while llms.txt is an optional, human-readable summary that points models to your key content. llms.txt cannot block or allow crawling.
Where do I put the llms.txt file?
Serve it at the root of your domain so it loads at yourdomain.com/llms.txt as plain text. On Next.js you can place a static file in the public folder or generate it dynamically with a Route Handler.
Should I create an llms.txt file for my blog?
It is optional. There is no confirmed benefit for blog visibility, so only add one if it is automatic to maintain or if you publish documentation that coding assistants may read. Otherwise focus on answer-first content and technical SEO.
Sources & Citations
- 1.The /llms.txt file (proposal) — llmstxt.org (Answer.AI)
- 2.AI features and your website — Google Search Central
- 3.Google says llms.txt is purely speculative for now — Search Engine Journal