llms.txt checker
llms.txt is a proposed Markdown file at your site's root that gives AI agents a short summary and links to your key pages. Only the H1 is required. Enter your domain to check whether the file exists, follows the spec and has working links. No major AI service we checked documents that it reads the file.
What is an llms.txt file?
llms.txt is a proposal that Jeremy Howard published at llmstxt.org in September 2024. Version 2 came in August 2026. It is a proposal, not a standard.
The file is Markdown: a short summary of your site and links to the pages that explain it, so an agent doesn't have to read the whole site. The spec says it was mainly meant for use when an AI answers a question, not for training, and that it is used mostly for software documentation.
The spec explains the difference itself: robots.txt says which access is okay, while llms.txt is used on request, when an agent needs information about your site. robots.txt decides which crawlers may read your site.
- llmstxt.org: The /llms.txt file, version 2Last checked November 10, 2026
Does llms.txt really work?
What each service's own documentation says about llms.txt. So far, the services we checked don't document reading it.
| Service | What its documentation says | Source |
|---|---|---|
| Google Search | What its documentation saysSays you don't need new files for its AI features: “You don't need to create new machine readable files, AI text files, or markup to appear in these features.” The page doesn't name llms.txt. | SourceGoogle Search Central: AI features and your websiteLast checked November 7, 2026 |
| Chrome Lighthouse | What its documentation saysHas an llms.txt audit. A server error when fetching the file is flagged; a missing file (404) is marked not applicable, because the file is optional. | SourceChrome for Developers: llms.txt auditLast checked November 7, 2026 |
| OpenAI | What its documentation saysDoesn't mention llms.txt in its crawler documentation. | SourceOpenAI: Overview of OpenAI crawlersLast checked November 7, 2026 |
| Anthropic | What its documentation saysDoesn't mention llms.txt in its article on how it crawls the web. | SourceAnthropic: Does Anthropic crawl data from the web?Last checked November 7, 2026 |
| Perplexity | What its documentation saysDoesn't mention llms.txt in its crawler documentation. | SourcePerplexity: Perplexity crawlersLast checked November 7, 2026 |
“Doesn't mention” means the documentation we read doesn't mention the file. It doesn't mean the service is proven not to read it.
Is llms.txt needed?
Not for Google. Google says you don't need to create new machine readable files or AI text files to appear in AI Overviews and AI Mode.
The spec itself says the file is used mostly for software documentation, where coding agents look up how a library or an API works.
For a store, it is your choice. The file is small and cheap to add, but no service we checked documents that it changes what it says about your store.
For your product pages, the services document other things: check a product page for ChatGPT shopping.
How do I write an llms.txt?
The format, in the order version 2 of the spec gives it:
- Start with an H1 with your store's name, like
# Acme AB. It is the only required part. - Add a blockquote with a short summary: what you sell and what someone needs to know to understand the rest of the file. A blockquote starts with
>. - If you like, add paragraphs or lists with more detail. Don't use headings here.
- Add sections under H2 headings, each with a list of links:
- [Name](url), optionally followed by:and a note about the page. - Put secondary links in a section called
## Optional. By convention, an agent can skip them when it needs a shorter context. - Save it as a text file at
/llms.txton your domain. Keep it small enough to fit in an AI model's context; the spec gives no size.
Version 2 also suggests Markdown versions of your pages, at the same address with .md added, and linking to them with rel="alternate" type="text/markdown". The checker counts links to .md versions, but links to ordinary pages are not an error.
- llmstxt.org: The /llms.txt file, version 2Last checked November 10, 2026
Example for an online store
# Acme AB
> Acme AB is an online store for outdoor clothing. This file lists the pages that describe our products, delivery, returns and sizes.
## Products
- [Jackets](https://acme.example/collections/jackets): All jackets, with prices and sizes
- [Trousers](https://acme.example/collections/trousers): Hiking and rain trousers
- [Base layers](https://acme.example/collections/base-layers)
## Shipping and returns
- [Shipping](https://acme.example/pages/shipping): Delivery times and costs
- [Returns](https://acme.example/pages/returns): How to return an item
## Size guide
- [Size guide](https://acme.example/pages/size-guide): Measurements for each size
## Optional
- [About Acme AB](https://acme.example/pages/about)
- [Care instructions](https://acme.example/pages/care)This is an example with a placeholder store, Acme AB. Replace the name, the summary and the links with your own.
Can I add llms.txt on Shopify?
Every Shopify store already has one. By default, Shopify serves /llms.txt and /llms-full.txt with the same content as the store's /agents.md, which Shopify calls the canonical agent-discovery document.
To change it, go to Online Store > Themes > Edit code and add a template: templates/agents.md.liquid changes all three files, and templates/llms.txt.liquid changes only /llms.txt. The file is served at your primary domain, without a language or Markets folder.
Shopify's default file mirrors agents.md and doesn't necessarily follow the llmstxt.org format, so the checker may show format findings for it. Shopify says that for most stores, the managed file is all you need. Changing it promises no effect on what AI services say.
- Shopify: llms.txt.liquidLast checked November 10, 2026
- Shopify changelog: Customize /llms.txt, /llms-full.txt and /agents.mdLast checked November 10, 2026
What is llms-full.txt?
llms-full.txt is a convention that some documentation sites publish: the whole documentation in one Markdown file. OpenAI, for example, publishes one for its commerce documentation. Version 2 of the llms.txt spec doesn't mention it.
The checker shows whether your site has an llms-full.txt, but doesn't read or judge it.
- OpenAI Commerce documentationLast checked November 7, 2026
- llmstxt.org: Changes in version 2Last checked November 10, 2026
Frequently asked questions
What is the difference between llms.txt and robots.txt?
robots.txt tells crawlers which parts of your site they may read. llms.txt gives an agent a summary of your site and links to your key pages when it needs information. The llms.txt spec describes the difference that way itself.
Where do I put llms.txt?
At the root of your domain, as yourstore.com/llms.txt. Version 2 of the spec also allows files on subpaths, covering the pages under them. This checker reads only the root file.
Does Google use llms.txt?
Google says you don't need new machine readable files or AI text files to appear in its AI features, and that page doesn't name llms.txt. Chrome's Lighthouse has an llms.txt audit, but that checks the file. It isn't Google Search reading it.
Does ChatGPT read llms.txt?
OpenAI's crawler documentation doesn't mention the file. That means OpenAI doesn't document reading it, not that it never does.
Is there an llms.txt validator?
Yes, this page. It checks your root llms.txt against version 2 of the spec at llmstxt.org: the H1, the headings and the links in each file list. It also checks whether up to 10 links on your domain work, and whether you have an llms-full.txt.
Can llms.txt block AI crawlers?
No. llms.txt describes your site; it doesn't allow or block anything. Crawler access is set in robots.txt: check your robots.txt for AI crawlers.
A text file can't tell you what AI says about your store. Ansedd shows what ChatGPT, Gemini and Google's AI Overviews recommend when buyers ask, and which sources they rely on.
Book a demo