llms.txt Validator
Check whether your llms.txt follows the llmstxt.org spec and if the optional llms-full.txt companion is well structured — no account required.
No data is stored or shared.
Understand llms.txt
What is llms.txt and why it matters for AI agents
llms.txt is a Markdown file at your domain root (/llms.txt) that gives LLMs and agents a curated map of your site — title, summary, and links to the most relevant content.
It does not replace robots.txt or sitemap.xml. It is optional for Google Search, but Lighthouse Agentic Browsing already audits its presence as an agent discoverability signal.
This validator checks structure and link format only — it does not test whether each listed URL returns 200. Missing llms.txt does not hurt Google rankings.
Why validate
Three good reasons to check now
llmstxt.org spec
H1, blockquote, H2 sections, and absolute links — the spec defines the format agents expect.
Agent readiness
Assistants with limited context windows spend fewer tokens when your site offers a clear Markdown index.
llms-full.txt companion
Sites with expanded context can publish llms-full.txt — we validate both without requiring the companion.
How it works
Diagnosis in three steps
Enter your domain
Type your site address. Accepts example.com, www, or a full URL.
Automatic analysis
We fetch /llms.txt and, if present, /llms-full.txt and validate structure.
Fix with clarity
A table showing what is good, what to improve, and how to fix each item.
FAQ
Questions about llms.txt
What is an llms.txt file?
A Markdown file at /llms.txt that summarizes your site's purpose and lists links to relevant content, following the proposal at llmstxt.org. It is aimed at LLMs and agents at inference time, not traditional rankings.
Does Google require llms.txt to rank?
No. Google's official generative AI optimization guide (2026) states llms.txt is not needed for Search or AI Overviews. It may still help other systems that choose to read it.
What is llms-full.txt?
An optional companion with expanded context (convention inspired by llms-ctx-full.txt). It is not part of the canonical spec — we validate it when present without penalizing absence.
How is llms.txt different from robots.txt?
robots.txt controls what crawlers may fetch. llms.txt invites agents to read a curated summary — editorial opt-in, not an access block.
Does Lighthouse check llms.txt?
Yes. In Lighthouse's experimental Agentic Browsing category, the audit fetches /llms.txt on your domain the way an AI agent would. If the file is missing (HTTP 404), the check is marked N/A — llms.txt is optional and does not fail the audit. If the server returns an error (5xx, timeout, or block), the check fails because an agent could not read your guide. This measures agent accessibility, not Google Search rankings.
Do I need .md links in the listed URLs?
The spec recommends Markdown versions of pages (same URL + .md). For documentation sites, pointing to .md improves LLM readability — a recommendation, not a requirement.