Free tools

llms.txt generator

Enter your domain. We read your sitemap, pull the real title and description of up to 20 key pages, and draft an llms.txt file you can edit, copy or download.

What the generator does

It looks for your sitemap in robots.txt and at the standard paths, skips pages that rarely help an AI tool understand a site (tag and category archives, pagination, cart and account pages), and takes the shallowest pages first, because the homepage, pricing and top-level pages usually describe a business best. For each one it fetches the page title and meta description and groups them into sections such as Main pages, Guides and articles, Documentation and Products. You choose which pages stay in, and edit the name and summary.

The format, in one example

# Acme Plumbing

> Licensed plumbers in Austin, Texas. Same-day repairs, water heater installs and
> drain cleaning for homes and small businesses. Prices from $89.

## Main pages

- [Services](https://acme.example/services): repairs, installs and maintenance
- [Pricing](https://acme.example/pricing): call-out fee and typical job prices

## Guides and articles

- [Tankless vs tank water heaters](https://acme.example/blog/tankless): costs and lifespan

## Optional

- [About us](https://acme.example/about)

The proposal at llmstxt.org asks for an H1 with the site or project name, a short summary in a blockquote, and H2 sections of links, each with an optional note after a colon. A section named Optional marks links a tool can skip when it is short on context.

Write a summary a model can quote

The blockquote is the part most worth your time. Say what you sell, to whom, where, and one concrete fact such as a starting price or coverage area. “Licensed plumbers in Austin, prices from $89” can be repeated in an answer. “Your trusted partner for all your needs” cannot.

Be realistic about what it does

llms.txt is useful for AI coding assistants and agents that read a site on request, and it costs almost nothing to publish. It is not a ranking signal: Google's AI features guidance says no special AI text files are needed, and the AI search engines have not said they read it when choosing sources. What does move AI answers is the same work that moves search results: pages crawlers can read, specific facts, and being named on the pages AI engines already cite. Check the first part with our AI crawler checker, and read AEO vs GEO vs SEO for the rest.

Questions

What is llms.txt?
A Markdown file at the root of a website (yoursite.com/llms.txt) that gives AI tools a short summary of the site and links to its most useful pages. Jeremy Howard of Answer.AI proposed the format in September 2024 at llmstxt.org.
Does Google use llms.txt?
Google's AI features guidance says you do not need special AI text files to appear in AI Overviews or AI Mode, and no major AI company has said its crawler reads it when deciding what to cite. Treat it as cheap, low-risk documentation for AI tools and coding assistants, not as a ranking factor.
Where do I put the file?
Upload it as a plain text file named llms.txt to the root of your domain so it loads at https://yoursite.com/llms.txt. On WordPress, an SEO plugin or a file manager can do this; on Shopify and similar hosted platforms you usually need an app or a redirect.
How is llms.txt different from robots.txt and a sitemap?
robots.txt tells crawlers what they may fetch. A sitemap lists every URL for search engines. llms.txt is a short, human-written guide to the pages that best explain the site, with a sentence about each.
What is llms-full.txt?
A companion file some sites publish with the full text of their documentation in one Markdown file, so an AI tool can read everything in one request. It is a convention used by documentation platforms, not part of the original proposal.

More free tools

Robots.txt generator

Build a robots.txt that allows AI search crawlers and blocks AI training crawlers, with a WordPress preset.

AI crawler checker

Shows which AI crawlers your robots.txt lets in: GPTBot, OAI-SearchBot, ClaudeBot, PerplexityBot, Google-Extended and more.

Meta tag checker

Title, meta description, canonical, robots, H1 and Open Graph tags for up to 10 pages, with length checks and duplicates.

Sitemap checker

Finds every sitemap a site declares, counts the URLs, checks lastmod dates and spot-checks that listed URLs return 200.

Redirect checker

Tests http, https, www and non-www versions of a site and shows every redirect hop, so you can see if they all land on one URL.

Schema markup generator

Build JSON-LD for Organization, LocalBusiness, FAQ, Product and Article pages, ready to paste into your site.

Keyword density checker

Word count and the most repeated words and phrases in your text, plus how often a target keyword appears. Runs in your browser.

SERP snippet preview

See how your title and meta description may look in Google on desktop and mobile, and where they get cut off.

Open Graph checker

og:title, og:description, og:image and twitter:card tags for up to 5 pages, with a preview of the shared link card.

H1 checker

The H1 heading of up to 10 pages, flagging pages with none or more than one.

Canonical tag checker

Whether each page's canonical points to itself, is missing, or tells Google to index a different URL.

Hreflang checker

Hreflang tags, language and region codes, x-default and return links between language versions.

Core Web Vitals checker

Real-user LCP, INP and CLS from the Chrome UX Report plus a Lighthouse lab test, on mobile or desktop.