Maruo Studio › llms.txt generator

Free llms.txt generator and checker

Can ChatGPT, Perplexity, Claude and Copilot read your site? Enter its address: the tool checks your robots.txt, validates your llms.txt file, looks for a sitemap and structured data, then helps you generate your llms.txt.

Checking… (5 to 10 seconds)

  • Free, no sign-up
  • 10 crawlers checked
  • No cookies, no tracking
  • llmstxt.org format, version 2

Generator

llms.txt generator: create your file

Fill in the fields, copy the result and upload it to the root of your site, at example.com/llms.txt. After a check, the fields are prefilled with the information from your home page.

# Martin Plumbing

> Plumber and heating engineer in Leeds: repairs and bathroom renovation.

The format follows the llmstxt.org proposal: a title, a summary, then sections of Markdown links. Pages listed under “Optional” are the ones an AI tool may skip when it is short on space.

How to use it

How to use the tool in 3 steps

Allow two minutes to check the site and create the file, whatever software runs your website.

  1. Enter your site's address

    The tool reads public files, the way a crawler would: the home page, robots.txt, the sitemap and llms.txt. The result arrives in 5 to 10 seconds.

  2. Read the score and the priorities

    You get a score out of 100, the status of each AI crawler and a “Where to start” list, sorted by importance.

  3. Generate your llms.txt

    The generator fields are prefilled. Add your pages, copy or download the file, then upload it to the root of the site.

Transparency

llms.txt validator: what the tool checks, and how the score is calculated

No black box: here are the six checks and the points each one is worth. The total is 100.

CheckWhat the tool looks atPoints
AI crawler accessThe robots.txt rules for six crawlers: GPTBot, OAI-SearchBot, PerplexityBot, ClaudeBot, Google-Extended and Bingbot. The points are split between them.30
Indexable home pageThe page answers with status code 200 and carries no noindex directive.20
Structured dataAt least one JSON-LD block on the home page. The tool lists the types it finds.15
llms.txt filePresent, served as text and not as HTML, with a title, a summary and links. An incomplete file earns 8 points.15
SitemapA valid XML sitemap, declared in robots.txt or located at /sitemap.xml.10
Title and meta descriptionBoth are present on the home page. The title alone earns 5 points.10
Total100
  • 75 and aboveYour site is wide open to AI assistants.
  • From 45 to 74Your site is partly readable by AI assistants.
  • Below 45Your site is hard for AI assistants to read.

The tool also shows the Content Signals in robots.txt, without counting them in the score: a line such as Content-Signal: search=yes, ai-input=yes, ai-train=no tells AI systems whether they may use your pages for search, to answer users, or for training (format proposed on contentsignals.org).

The score is indicative. It measures whether AI assistants can read your site, not whether they cite it. To find out, ask them the questions your customers ask and look at the sources they name.

Robots.txt

The 10 crawlers checked in your robots.txt

Each AI assistant uses one or more crawlers. Some serve search, others collect pages to train models: the difference matters when you decide who to let in.

CrawlerCompanyWhat it doesIn the score
OAI-SearchBotOpenAIPowers ChatGPT searchYes
GPTBotOpenAICollects pages to train modelsYes
ChatGPT-UserOpenAIVisits a page when a ChatGPT user asks for itShown
PerplexityBotPerplexityBuilds Perplexity's search indexYes
ClaudeBotAnthropicCollects pages to train Claude modelsYes
Google-ExtendedGoogleA setting that allows or refuses the use of your content by Gemini. No effect on Google SearchYes
GooglebotGoogleCrawls the web for Google SearchShown
BingbotMicrosoftCrawls the web for Bing, which Copilot relies onYes
Applebot-ExtendedAppleA setting that allows or refuses the use of your content by Apple IntelligenceShown
CCBotCommon CrawlBuilds an open archive of the web, used by many AI projectsShown

How to read the statuses

  • allowed: no rule keeps this crawler out of the site.
  • allowed (with exclusions): the crawler gets in, but some folders are closed to it.
  • blocked: a Disallow: / rule targets it, directly or through the general rule User-agent: *.
  • could not be checked: the robots.txt file could not be read.

Allowing AI crawlers

User-agent: OAI-SearchBot
Allow: /

User-agent: GPTBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: ClaudeBot
Allow: /

A crawler with no rule of its own follows the general rule User-agent: *. If that rule allows everything, you have nothing to add: the lines above are mostly there to lift an existing block.

Installation

Where to put your llms.txt file

The file goes at the root of the site, next to robots.txt, and must display as plain text at example.com/llms.txt.

Depending on your platform

  • WordPress: the Yoast SEO and AIOSEO plugins can generate an llms.txt and keep it up to date. Otherwise, upload the file to the root with your host's file manager.
  • Wix: the platform generates an llms.txt for each site.
  • Static or custom site: add the file to the root of the project.

After uploading

  • Open the file's address in a browser: you should see text, not a page of your site.
  • Run the check again at the top of this page.
  • Optional: point to the file from the <head> of your pages with <link rel="describedby" href="/llms.txt">, as version 2 of the proposal describes.

Limits

What the tool cannot see

  • Blocks outside robots.txt. A firewall or a host can refuse AI crawlers without robots.txt saying so. The tool identifies itself under its own name, not as GPTBot, so it cannot observe that refusal.
  • Inner pages. Structured data, title and description are read on the home page only.
  • Citations. A perfectly readable site may never be cited if its pages do not answer the questions people ask.

Your data

The tool sets no cookies and asks for no sign-up. It has no database: we do not keep the addresses that are checked. Only public files are read.

Readable does not mean cited

A site that is open to crawlers is only the first step. To know whether ChatGPT, Perplexity and Copilot actually cite you, ask them the questions your customers ask and see which sites they name. Feedback or a bug to report: [email protected].

Check another site

Frequently asked questions

llms.txt and AI crawlers: what you need to know

What is an llms.txt file?

llms.txt is a plain-text file in Markdown format, placed at the root of a website (example.com/llms.txt). It introduces the site in a few lines and lists its most useful pages, so AI agents and tools can find the essentials quickly. It is a proposed standard, published on llmstxt.org in 2024 and revised in August 2026.

Is the llms.txt generator really free?

Yes. It works without sign-up, without an email address and without cookies. You can check several sites and generate as many files as you need.

How do I validate an llms.txt file?

Enter your domain at the top of this page. The checker fetches /llms.txt and verifies that it is served as plain text rather than HTML, and that it has a title (#), a summary (>) and Markdown links. It then shows the first lines of the file, so you can read what AI tools receive.

Does llms.txt improve Google rankings?

No, not directly. Google's documentation says no special AI file is needed to appear in its AI answers. The file is for AI agents and tools that choose to read it. To be cited by AI assistants, what matters most is still letting them access the site, having a sitemap, structured data and pages that answer questions clearly.

Where do I put the llms.txt file?

At the root of the domain, at https://example.com/llms.txt, served as plain text and encoded in UTF-8. On WordPress, the Yoast SEO and AIOSEO plugins can generate it. Otherwise, upload it to the root with your host's file manager.

How do I know if my site blocks ChatGPT or Perplexity?

Read the site's robots.txt file and look for rules that target GPTBot, OAI-SearchBot, PerplexityBot, ClaudeBot or Google-Extended, or a general rule that blocks everything. The checker on this page does it automatically. Note that some hosts and firewalls also block AI crawlers without going through robots.txt.

Should I allow GPTBot?

That is your call. GPTBot collects pages to train OpenAI's models. The crawler behind ChatGPT search is OAI-SearchBot: that is the one to let through if you want to appear, with a link, in ChatGPT's answers. You can still block GPTBot alone if you refuse training.

What does a score below 45 mean?

The tool found a serious obstacle: AI crawlers blocked, a home page that is unreachable or marked noindex, no sitemap and no structured data. The “Where to start” list under the score gives the fixes in order.

Does the tool work with WordPress, Wix or Shopify?

Yes. The tool reads public files (home page, robots.txt, sitemap, llms.txt), whatever software built the site.

Sources, accessed on 10 November 2026: llmstxt.org, and the crawler documentation of OpenAI, Perplexity, Anthropic, Google, Bing, Apple and Common Crawl.