Skip to content

Free AI tool · follows the llmstxt.org proposal

llms.txt generator and validator.

Fill in your site’s name, a short summary and the pages worth reading, and get an llms.txt in the format the llmstxt.org proposal sets out. Or paste a file, or fetch one from any site, and check it line by line. llms.txt is a proposal, not a standard: this tool checks the shape the proposal describes and makes no claim about who reads it.

Mode

The key facts an agent needs to make sense of the rest.

Plain text or lists. Headings are not allowed here.

Section 1
Section 2
Section 3
llms.txtMatches the proposal
Errors
0
Warnings
0
H2 sections
3
Size
694 B
  • NoteLine 16: An "Optional" section: by convention, secondary links an agent can skip.

Rules applied, and where we read them

llms.txt is a proposal, not a standard. This tool checks the format the proposal describes and makes no claim about which services read the file.

What the proposal says

A short, structured guide to your site for AI agents.

  • 01

    What the format asks for

    One H1 with the site or project name is the only required part. Then a blockquote summary, optional notes, and H2 sections that each hold a list of links, every link optionally followed by a colon and a note.

  • 02

    What it does not do

    llms.txt does not control crawling; robots.txt does. It is a guide an agent can read when it needs to know about your site. The proposal’s author expected it to be used when answering questions rather than for training.

  • 03

    Checked line by line

    The validator reports errors, which break the format, and warnings, which the proposal advises against, each with its line number. A shared link carries your file in the address, not to our server.

FAQs · llms.txt generator

llms.txt · frequently asked questions

What the file is, what the proposal requires, and what is known about who reads it.

A markdown file at /llms.txt that gives AI agents a short overview of a site and links to the pages worth reading, ideally in markdown. It is described in a proposal at llmstxt.org, first published by Jeremy Howard in September 2024 and revised as version 2 in August 2026.
No. It is an open proposal maintained on GitHub and open to community input, not a standard from a body such as the IETF or W3C. This tool checks files against the proposal as published on llmstxt.org on the date shown under the validator.
This tool makes no claim about which services read it. One documented use: Chrome’s Lighthouse includes an llms.txt audit in its agentic browsing checks, which flags a server error when fetching the file and marks a missing file as not applicable.
That the file opens with an H1, the only required part; that a blockquote summary follows; that nothing before the first H2 is a heading; and that each H2 section is a list of markdown links, each optionally followed by a colon and notes. Errors break the format, warnings are advice.
By convention it holds secondary links an agent can skip when it needs a shorter context. Version 2 of the proposal keeps the convention but drops the special meaning earlier tools gave it.
At the root, /llms.txt, or at any path within the site: the proposal says a file covers the pages under its path, and where more than one applies, agents should use the most specific. The fetch button here reads the root file.
No. robots.txt says what crawlers may fetch and a sitemap lists pages for search engines. llms.txt is a curated guide an agent reads on demand. Use the robots.txt generator and AI crawler checker for crawling rules.

Next step

Making your product easy for AI agents to use?

QalbIT builds AI features into web and mobile products, from retrieval over your own documents to agents that act on them.

AI development

Keep exploring

More free tools

More free tools

Each one opens on a worked example and shows its answer without a signup.

All free tools