Free ai search readiness check
llms.txt Validator
llms.txt is a Markdown file that gives language models a short, curated map of a site. Check that yours is published, follows the proposed format and links to pages that work.
Validate llms.txt
Enter the address of the site. The checker reads /llms.txt and /llms-full.txt.
Why use the llms.txt Validator
Format checked
The file must be served as plain text or Markdown and start with an H1 title followed by a short summary.
Links tested
A sample of the links in the file is requested, so you know it does not send models to dead pages.
The full variant
llms-full.txt, the version with the content inlined, is detected and its size reported.
Agent discovery too
MCP server cards, API catalogs and OpenAPI documents are listed if the site publishes them.
When to use the llms.txt Validator
Publishing llms.txt
Validate the file the first time you publish it.
Docs sites
Developer documentation benefits most. Check the file after every docs release.
Generated files
Plugins and frameworks generate llms.txt. Confirm the output is valid and the links resolve.
Agent readiness
Pair it with the discovery files so agents can find your API as well as your content.
Content migrations
Old links in llms.txt break quietly when urls change.
Comparing sites
See how other sites in your field structure their llms.txt.
Understanding llms.txt
What llms.txt is
llms.txt is a proposal, published in 2024, for a Markdown file at the root of a site. It gives a language model a curated summary and the links that matter most, without the navigation, scripts and ads of the HTML pages.
It is an emerging convention. Some AI tools and agent frameworks read it, the major search engines do not use it for ranking. Treat it as cheap, useful documentation rather than an SEO lever.
The format
- 1Title. One H1 with the name of the site or project.
- 2Summary. A blockquote with a short description of what the site is.
- 3Details. Optional paragraphs with anything a model needs to know.
- 4Sections. H2 sections with Markdown link lists, each link optionally followed by a short note.
llms.txt and llms-full.txt
llms.txt is the index. llms-full.txt is the same content with the linked pages inlined, so a model can read everything in one request. Keep llms-full.txt to a size a model can actually use.
Privacy, safety and limits
The check runs on Aback servers. It identifies itself as AbackAuditBot, and when it tests what an AI crawler receives it sends that crawler's user agent from the same servers. It never sends a cookie or a password and never changes the site.
It cannot tell you whether an assistant will cite you. It tells you whether the assistant can reach and read your pages, which is the part you control.
Related tools and guides
Frequently asked questions
Do I need an llms.txt?
It is optional. It costs little to publish and helps agents and AI tools that read it, especially for documentation and API sites. It is not a ranking factor for search engines.
Does ChatGPT read llms.txt?
There is no public commitment from the major assistants to read it. Some developer tools and agent frameworks do. Publish it for those, without expecting it to change how assistants rank you.
Where does the file go?
At the root of the site, at /llms.txt, served as text/plain or text/markdown.
What should I link to?
The pages a model needs to understand and use your site: the main docs, the API reference, pricing, the policies. Not every page.
Why do some of my links fail?
The sampled links answered with an error or were too large to read. Update moved urls and keep linked files to a reasonable size.
Is there a generator?
Yes. The llms.txt generator writes a valid file from a few fields and a list of links, in your browser.
What are agent discovery files?
Machine readable files such as an MCP server card, an API catalog or an OpenAPI document that let agents find and call your services. They are reported as information.