Public AI Access tool

llms.txt Checker

Verify if your website has a /llms.txt file — the emerging standard for letting AI assistants like ChatGPT, Claude, and Perplexity understand your site. Get quality scoring and recommendations.

Typical check: 2sNo paid API requiredCrawler policy checksStructured extraction signalsTrust-focused guidance

Check public AI access Browse Public AI Access

Typical time

Access

Open

Processing

Live

Intent

Public AI Access

What it checks

llms.txt Checker coverage

llms.txt Checker

Check if your site has an llms.txt file for AI crawlers.

Machine readability

Review semantic structure, metadata, schema, and crawl permissions.

Citation signals

Look for clear answers, factual density, authorship, and source context.

Public AI access next steps

Prioritize changes that help answer engines quote the right content.

Methodology

How the result is produced

1Fetches /llms.txt from the target domain's root and checks for presence, valid markdown formatting, and content quality.
2Scores the file on 5 key factors: file existence, proper heading structure, site description clarity, key page links, and documentation references.
3Also checks if the site's robots.txt allows AI crawlers to access the llms.txt file.

Next steps

How to act on the result

Create a /llms.txt file at your domain root — use markdown format with a clear site title and description.
List your 5-10 most important pages with brief descriptions — these help AI assistants understand your site structure.
Include links to documentation, API references, or help articles if applicable.
Add a ## Contact or ## About section with your organization name and purpose.
Test that the file is publicly accessible and not blocked by robots.txt or authentication.

Interpretation

Read the result without guessing

What the result means

llms.txt is a context file, not a ranking shortcut.
It is useful only when it is reachable, curated, and aligned with sitemap and crawl policy.
A copied sitemap is less useful than a short list of important public pages.

Evidence to keep

robots.txt, llms.txt, meta robots, schema, canonical, and rendered answer sections.
The specific public pages that should be easier for AI systems to parse.
Source, author, date, and factual-density signals for pages that should be cited.

Best next fix

Align robots.txt, llms.txt, sitemap, and canonical signals.
Add direct-answer sections, semantic HTML, and accurate JSON-LD.
Improve source clarity, then retest the same priority URLs after crawl refresh.

Related diagnostic workflows

llms.txt is not detectedA practical setup check for sites adding an llms.txt context file without treating it as a ranking shortcut.Open workflow AI crawler appears blockedA policy-first workflow for separating classic search bots, retrieval bots, and training controls.Open workflow

Use cases

When to use the llms.txt Checker

Public AI access signals

Improve crawl access, extractability, structured data clarity, and source context.

Content extraction QA

Check whether pages are structured for snippets, answers, and source references.

Crawler policy review

Align robots, metadata, schema, and llms.txt with your public AI crawl policy.

Popular checks

Try llms.txt on common domains

llms.txt for openai.com llms.txt for perplexity.ai llms.txt for anthropic.com llms.txt for github.com llms.txt for cloudflare.com llms.txt for shopify.com

Next paths

Continue with the right follow-up

Use these pages when the result points to a broader check, a fix workflow, or a related technical question.

llms.txt Complete Setup Guide AI readiness checklist AI Readiness for Modern Websites

Fix workflows

Fix issues found by llms.txt

How to fix AI crawlers blocked by robots.txt

Separate AI retrieval, AI training, and classic search crawler rules so your policy matches what should be public.

Open fix guide

Frequently asked questions

llms.txt Checker common questions

Do I need an account to use the llms.txt Checker?+

No. Enter a URL or domain and run the check in your browser. Some results can be partial if the target site blocks requests or hides the data being checked.

How accurate is the llms.txt Checker?+

The llms.txt Checker runs live checks against the target website. Results reflect what was reachable at the time of the test, so retest after changing DNS, redirects, headers, or page content.

What is llms.txt and why does my site need it?+

llms.txt is an emerging standard (like robots.txt but for AI). It helps AI assistants like ChatGPT, Claude, and Perplexity understand your site structure, key pages, and documentation.

Where do I put the llms.txt file?+

Place it at the root of your domain: https://yourdomain.com/llms.txt. Use markdown format with headings, descriptions, and links to important resources.

Does llms.txt affect Google rankings?+

No. Treat llms.txt as a context file for some AI assistants and crawlers, not as a Google ranking requirement. Crawlability, useful content, internal links, and matching structured data still matter first.

Loading CheckWebs…

Public AI Access tool

llms.txt Checker

Verify if your website has a /llms.txt file — the emerging standard for letting AI assistants like ChatGPT, Claude, and Perplexity understand your site. Get quality scoring and recommendations.

Typical check: 2sNo paid API requiredCrawler policy checksStructured extraction signalsTrust-focused guidance

Check public AI access Browse Public AI Access

Typical time

Access

Open

Processing

Live

Intent

Public AI Access

What it checks

llms.txt Checker coverage

llms.txt Checker

Check if your site has an llms.txt file for AI crawlers.

Machine readability

Review semantic structure, metadata, schema, and crawl permissions.

Citation signals

Look for clear answers, factual density, authorship, and source context.

Public AI access next steps

Prioritize changes that help answer engines quote the right content.

Methodology

How the result is produced

1Fetches /llms.txt from the target domain's root and checks for presence, valid markdown formatting, and content quality.
2Scores the file on 5 key factors: file existence, proper heading structure, site description clarity, key page links, and documentation references.
3Also checks if the site's robots.txt allows AI crawlers to access the llms.txt file.

Next steps

How to act on the result

Create a /llms.txt file at your domain root — use markdown format with a clear site title and description.
List your 5-10 most important pages with brief descriptions — these help AI assistants understand your site structure.
Include links to documentation, API references, or help articles if applicable.
Add a ## Contact or ## About section with your organization name and purpose.
Test that the file is publicly accessible and not blocked by robots.txt or authentication.

Interpretation

Read the result without guessing

What the result means

llms.txt is a context file, not a ranking shortcut.
It is useful only when it is reachable, curated, and aligned with sitemap and crawl policy.
A copied sitemap is less useful than a short list of important public pages.

Evidence to keep

robots.txt, llms.txt, meta robots, schema, canonical, and rendered answer sections.
The specific public pages that should be easier for AI systems to parse.
Source, author, date, and factual-density signals for pages that should be cited.

Best next fix

Align robots.txt, llms.txt, sitemap, and canonical signals.
Add direct-answer sections, semantic HTML, and accurate JSON-LD.
Improve source clarity, then retest the same priority URLs after crawl refresh.

Related diagnostic workflows

Use cases

When to use the llms.txt Checker

Public AI access signals

Improve crawl access, extractability, structured data clarity, and source context.

Content extraction QA

Check whether pages are structured for snippets, answers, and source references.

Crawler policy review

Align robots, metadata, schema, and llms.txt with your public AI crawl policy.

Popular checks

Try llms.txt on common domains

llms.txt for openai.com llms.txt for perplexity.ai llms.txt for anthropic.com llms.txt for github.com llms.txt for cloudflare.com llms.txt for shopify.com

Next paths

Continue with the right follow-up

Use these pages when the result points to a broader check, a fix workflow, or a related technical question.

llms.txt Complete Setup Guide AI readiness checklist AI Readiness for Modern Websites

Fix workflows

Fix issues found by llms.txt

How to fix AI crawlers blocked by robots.txt

Separate AI retrieval, AI training, and classic search crawler rules so your policy matches what should be public.

Open fix guide

Frequently asked questions

llms.txt Checker common questions

Do I need an account to use the llms.txt Checker?+

No. Enter a URL or domain and run the check in your browser. Some results can be partial if the target site blocks requests or hides the data being checked.

How accurate is the llms.txt Checker?+

The llms.txt Checker runs live checks against the target website. Results reflect what was reachable at the time of the test, so retest after changing DNS, redirects, headers, or page content.

What is llms.txt and why does my site need it?+

llms.txt is an emerging standard (like robots.txt but for AI). It helps AI assistants like ChatGPT, Claude, and Perplexity understand your site structure, key pages, and documentation.

Where do I put the llms.txt file?+

Place it at the root of your domain: https://yourdomain.com/llms.txt. Use markdown format with headings, descriptions, and links to important resources.

Does llms.txt affect Google rankings?+