llms.txt Checker

Last updated:

Check if any website has a valid llms.txt file. Verify existence, format, structure, and completeness: the AI-readable index that helps ChatGPT, Perplexity, and other AI systems understand your site.

What Is llms.txt?

llms.txt is a plain text file placed at the root of a website, for example, yoursite.com/llms.txt, that helps large language models (LLMs) and AI systems understand the site's structure and most important content.

Think of it as a curated, AI-readable index of your site. While sitemap.xml lists all your URLs for search engine indexing, llms.txt tells AI systems which pages matter most and what they contain, in plain language.

The format was proposed in 2024 and has quickly gained adoption as part of the broader GEO (Generative Engine Optimization) toolkit.

What This Checker Tests

When you enter a domain, this tool checks the following:

  • File existence: Is there a file at /llms.txt on the root domain?
  • HTTP status: Is it returning 200 OK? A 404 means no file exists.
  • Content type: Is it served as text/plain as the spec recommends?
  • H1 header: Does the file start with an H1 (site name) as required by the format?
  • Description present: Is there a short description following the H1?
  • Sections (H2): Are pages organized under H2 section headers?
  • Linked entries: Does the file contain Markdown-formatted links with descriptions?
  • llms-full.txt: Does the site also provide the optional full-text companion file?

The llms.txt Format

A valid llms.txt file follows this structure:

# Site Name

Brief 1-3 sentence description of what the site does and who it serves.

## Services

- [Service Page](https://example.com/services/): What this page covers.
- [Another Service](https://example.com/other/): Description.

## Blog / Guides

- [Key Article](https://example.com/article/): What this article covers.

## Tools

- [Free Tool](https://example.com/tools/tool/): What the tool does.

Use our free llms.txt Generator to build a properly formatted file for your site. For a complete guide to the format and strategy, read our llms.txt Complete Guide.

Why llms.txt Matters for AI Visibility

AI search platforms like ChatGPT, Perplexity, and Google AI Overviews retrieve and cite content from the web. The clearer and more structured your site appears to these systems, the more accurately and frequently they will reference your business.

llms.txt is part of a broader technical foundation for AI search visibility that includes:

  • robots.txt, allowing AI crawlers to access your content
  • Schema markup, structured data for entity and content verification
  • llms.txt, curated navigation guide for AI systems
  • Passage-level content: clear, extractable answer blocks

Use the AI Search Visibility Checker to get a comprehensive readiness audit that goes beyond just llms.txt.

Related Tools

Next steps

llms.txt Checker related tools and articles

Continue with the closest follow-up checks and guides based on this tool's topic, crawl intent, and optimization workflow.

llms.txt Checker: FAQ

Which URL does the checker request?
It takes the hostname from your input and checks https://hostname/llms.txt plus https://hostname/llms-full.txt. Paths, query strings, a typed http scheme, and custom ports are not preserved, so the file is always checked at the HTTPS site root.
What counts as an existing llms.txt file?
The checker treats HTTP 200 as found. Other statuses are reported as missing. It expects a text/plain Content-Type and flags other types, even though some valid deployments may use another text-oriented media type.
Which structure checks are performed?
It looks for one H1 line, a following non-heading description line, at least one H2 section, and at least one bullet Markdown link with an absolute HTTP or HTTPS URL. These are simple text-pattern checks, not a full Markdown or llms.txt parser.
What does the llms-full.txt badge mean?
It only means the root llms-full.txt request returned HTTP 200. The checker does not parse or grade that file's content, and llms-full.txt is optional.
Does passing improve rankings or guarantee AI citations?
No. llms.txt is a voluntary, evolving convention. A clean file may help a compatible system navigate selected resources, but it does not force crawling, indexing, retrieval, ranking, or citation.
Why can the checker fail when the file opens for me?
The proxy or direct fallback can time out, encounter bot protection, receive a different CDN response, or be blocked by CORS on the browser fallback. Also confirm the file is publicly available over HTTPS at the exact root path.
Which llms.txt issue should I fix first?
Serve the intended Markdown as a successful root response, then correct the Content-Type and add a concise H1, description, useful H2 sections, and absolute links to canonical pages. Keep the list curated and update it when important URLs change.
What data is sent during an llms.txt check?
The hostname is sent to Web Aloha's proxy so it can request the two public text files; if that fails, your browser may try the site directly. The checker displays up to 2,000 characters but does not include application logic that persists the file content.

Free 48-Hour Website Audit

Not sure what to fix first on your own website? We'll review it and tell you, in plain English. Free & non-obligatory.

Need Help With Your Website?

We help businesses build and optimize their online presence, let's talk.