Free llms.txt checker and validator

llms.txt checker and validator

Check the live /llms.txt file on a public website, or paste a draft to validate it before deployment. Both modes apply the same rules to the title, introduction, sections, Markdown links, malformed link syntax, duplicate destinations, and insecure HTTP URLs. Live mode also reports the response status, redirects, and content type.

llms.txt is an optional, emerging convention, most useful when a documentation or product team wants to point agents toward the pages that define its product, API, and policies. The checker currently requests the root /llms.txt file only; the llms.txt v2 proposal also permits scoped files such as /docs/llms.txt, which you can validate here by pasting their content.

Public website check Inspectable evidence Clear limitations

Methodology reviewed 2026-10-17

More free checks

Try the other free AI discovery checks

Each check looks at a different layer of AI discovery readiness. Run them together for a fuller picture, or open the complete audit for all of it at once.

Check robots.txt rules for documented AI crawlers

Enter a public hostname to test whether its deployed robots.txt policy allows, blocks, or has no matching restriction for documented AI crawler tokens at the root path.

Check AI crawler rules

Check how clearly your website identifies the business and its entities

Compare visible homepage identity with structured entities, graph identifiers, sameAs identity references, and trust signals.

Check structure and identity

Check Recipe structured data on a food publisher page

Check the actual public recipe page for Recipe JSON-LD, Google-required fields, and selected recommended properties.

Check Recipe schema

Build a starting llms.txt file

Fill in a title, short context, and the resource links you want to list, and this page builds a valid llms.txt file for you to review, edit, and publish.

Build llms.txt

Build a starting robots.txt from a declared policy goal

Choose a declared policy goal and this page builds robots.txt groups for the documented AI crawler tokens that goal has an explicit preference for, which you can review, edit, and publish.

Build robots.txt

Build a starting Organization JSON-LD block

Build Organization JSON-LD with a reusable #organization @id and optional identity-reference URLs.

Build JSON-LD

AI citation forensics

Paste a prompt and the source an AI answer cited. See which public evidence differs from your site, what is worth testing, and what no external audit can prove.

Compare the evidence

Business facts consistency checker

Compare the business name, phone, email, address, and official profiles stated on your homepage, About page, Contact page, and JSON-LD, and see where any value differs.

Check business facts

Website launch and migration check

Compare the new version of a site or page with the current live one under the same audit rules, and see regressions in crawler access, content, and identity before you launch.

Compare before and after

What this check looks for

See the public evidence behind the result

OpenForBots examines the relevant public page or resource, shows what it found, and explains what to review next.

1
Live mode checks the public /llms.txt file at the root of the website.
2
Live mode reports response availability, redirects, content type, and bytes read.
3
Paste mode validates draft or scoped llms.txt content in your browser without fetching any website.
4
Extracts the document title, introductory context, H2 sections, and Markdown links.
5
Identifies malformed link-like lines, duplicate destinations, and insecure HTTP URLs.
6
Separates file quality observations from unsupported ranking or citation claims.
7
Discloses that scoped llms.txt v2 files and rel="describedby" or Markdown alternate discovery links are outside the live check scope.

Example evidence result

The file is available but has limited introductory context

The live result uses the deployed page or resource and exact check time. This example shows the evidence structure, not a claim about a real domain.

Observed evidence

Observed source: https://example.com/llms.txt
Document title: found
Resource links: 12
Opportunity: add a concise factual introduction before the resource sections

Recommended next action

Add only accurate, maintained context; keep the file concise; and re-run the check after the deployed response changes.

Understand the result

What the check confirms—and what it cannot tell you

What it can confirm

Live mode: whether OpenForBots could retrieve a text response at the convention location.
What supported Markdown structure and links were observed in the file or pasted content.
Which file-quality issues and improvement opportunities were identified.

What remains unknown

llms.txt is not part of the Robots Exclusion Protocol and does not grant crawler permission.
A valid pasted draft shows only that the text is well formed. It does not show that the file is deployed, reachable, or served as text.
Live mode evaluates the root /llms.txt file only; a missing root file is not proof that no scoped llms.txt v2 file exists elsewhere.
A missing file is not proof that a website is inaccessible or unready for AI discovery.
A valid file does not guarantee provider support, indexing, ranking, citation, or model use.
The checker reviews file structure and links; it does not certify the factual accuracy of every linked page.

Learn and take action

Related guides and methodology

Don't have an llms.txt yet? Build one

Generate a starting llms.txt from a title, system context, and resource links.

Review the proposal, practical uses, adoption limits, and non-guarantees.

Place llms.txt in the wider access, content, structure, identity, and verification workflow.

Questions about this check

Is llms.txt required for ChatGPT, Claude, Perplexity, or Google AI features?

OpenForBots does not treat it as a universal requirement. Provider support varies and can change, so the checker reports the deployed file without converting the convention into a ranking guarantee.

Does llms.txt replace robots.txt or a sitemap?

No. robots.txt expresses crawler policy, while a sitemap supports URL discovery for systems that consume it. llms.txt is intended as a concise contextual resource index for tools that choose to use it.

Is a missing llms.txt file a critical failure?

No. Missing llms.txt is reported as an optional opportunity, not proof that the site is blocked, uncrawlable, unindexable, or unable to receive citations.

What is the difference between checking and validating llms.txt?

Checking requests the published /llms.txt file from a website and reports what the server returned. Validating examines the text itself. Live mode does both for the deployed file; paste mode validates a draft before you publish it, using the same structure rules.

Is pasted llms.txt content sent to OpenForBots?

No. Paste mode runs in your browser. The pasted text is not uploaded and is not included in analytics events. Relative links stay as written because a draft has no deployed location to resolve them against.

Does this checker find llms.txt files under subpaths such as /docs/llms.txt?

Live mode requests the root /llms.txt file only. The llms.txt v2 proposal permits scoped files and discovery links; to validate a scoped file, paste its content into paste mode.