What it checks
The Cyberbard llms.txt Generator is a free tool that validates a site's existing llms.txt and its links, and drafts a new llms.txt from the site's sitemap and navigation, with every link checked and descriptions that can be edited before download.
Validates your current file
Title heading, summary block, sections, link format and whether your key pages (home, about, contact) are listed, in English and common localised URLs.
Tests every link
Each link to your site in the file is requested. Broken links and redirects are listed so you can fix them.
Drafts from your real pages
Links come from your navigation and your sitemap, not from a guess. Login, cart, tag and file URLs are left out.
Sorted into sections
Products, Pricing, Docs, Blog, Company, Pages and Optional (the spec's section for skippable links), with a cap per section so one blog doesn't crowd out everything else.
Your language or English
Descriptions and section headings in your site's language (8 languages have localised headings), or in English if you prefer.
Edit, copy, download
The draft opens in an editor. Change anything, then copy it or download llms.txt.
How to use the llms.txt Generator & Validator
Enter your domain
Type example.com. For a site with language sections, enter the section (example.com/de/) to draft from those pages; the file itself always lives at the root.Review the current file (if any)
See what's missing or broken in the llms.txt you already publish.Edit the draft
Check the descriptions (they are written by AI or taken from your meta descriptions, so read them), remove pages you don't want listed and add any that are missing.Publish at /llms.txt
Download the file and upload it to your site's root so it is served at https://yourdomain/llms.txt as plain text.What this tool does, and what it doesn't (yet)
So you know exactly what the result covers, and where to look for the rest.
What it does
- Read /llms.txt (and /llms-full.txt if that's all there is) and check its structure against the llms.txt proposal
- Recognise key pages in English and localised forms (/ueber-uns, /a-propos, /会社概要, "关于我们" …)
- Test up to 40 of your own links in the existing file and report errors and redirects
- Collect up to 40 links from your navigation and sitemap, skipping login, cart, tag, feed and file URLs
- Load each page to confirm it works and to read its title and meta description
- Write one-line descriptions with AI (Google Gemini), in your site's language or English
- Fall back to your own meta descriptions when AI isn't available, and say so
Not covered (yet), and what to do instead
It doesn't generate llms-full.txt (the version with full page text).
Instead: Start with llms.txt; it's the file tools look for first.
Sites without a sitemap whose menus are built by JavaScript may yield very few links, because we read the HTML your server sends.
Instead: Add missing pages by hand in the editor, and consider publishing a sitemap.xml.
AI-written descriptions can be wrong or too generic.
Instead: Read every line before publishing; the editor is there for that.
We can't upload the file to your server.
Instead: Download it and upload it to your site root, or send it to your developer.
Links to other websites in your existing file aren't tested; we only request pages on your own domain.
Instead: Check external links by opening them.
Nobody can promise that a given AI assistant reads llms.txt (see the FAQ).
Instead: Treat it as a low-cost extra, not a replacement for crawlable pages and good structure.
What llms.txt is, and what it can and can't do
llms.txt is a plain Markdown file at the root of a website (/llms.txt) that gives AI systems a short, curated guide to the site: what it is, and which pages matter, with a one-line note for each. It was proposed by Jeremy Howard of Answer.AI in September 2024; the format is described at llmstxt.org.
The format
# Example Co
> Example Co makes accounting software for freelancers in Germany.
Optional extra context in plain paragraphs.
## Docs
- [Getting started](https://example.com/docs/start): Create an account and send a first invoice.
## Optional
- [Press kit](https://example.com/press): Logos and company facts.
Only the # title is required. A > summary, a few ## sections of links, and an ## Optional section (links an AI may skip when it is short on space) make up the rest.
Who reads it today
Be realistic about this. llms.txt is a proposal, not a standard, and at the time of writing none of the major AI search providers has documented that it uses llms.txt to decide what to cite. It is read by some developer tools and AI coding assistants, and documentation platforms publish it widely. That makes it a cheap, low-risk addition: it costs an hour, can't hurt, and gives any system that does read it a clean map of your site. It is not a substitute for pages AI crawlers can reach and understand (see the AI Crawler Checker).
How llms.txt differs from robots.txt and sitemap.xml
| File | Purpose | Audience |
|---|---|---|
| robots.txt | Says what crawlers may fetch | All crawlers |
| sitemap.xml | Lists every URL you want indexed | Search engines |
| llms.txt | A short guide to your most useful pages, with context | AI systems |
Good practice
- Lead with a factual summary: what you are, for whom, where. No slogans.
- List the pages that answer real questions: products, pricing, docs, key guides. Not every blog post.
- Keep links working: a broken link sends an AI to an error page. This tool tests them.
- Match the language your customers use. If you have language sections, it's reasonable to describe the main language in llms.txt and link the other language sections.
- Update it when your site changes, like a sitemap.
How this generator differs from most llms.txt generators
An honest comparison, including what we don't do.
Generates a draft file
Validates the file you already have
Tests every link before listing it
Uses your navigation, not just the sitemap
Descriptions in your site's language
Editor with copy and download
Generates llms-full.txt
Frequently asked questions
What is llms.txt?
A Markdown file at /llms.txt that gives AI systems a short guide to your website: a title, a one-paragraph summary, and lists of your most important links with a note for each. It was proposed in 2024 by Jeremy Howard (Answer.AI); the format is at llmstxt.org.
Do ChatGPT, Claude, Perplexity or Google use llms.txt?
At the time of writing, none of the major AI search providers has documented that it uses llms.txt for search or citations. Some developer tools and coding assistants read it. We recommend it as a cheap extra, not as a ranking lever, and we won't promise otherwise.
What is the difference between llms.txt, robots.txt and a sitemap?
robots.txt says what crawlers may fetch. sitemap.xml lists every URL you want indexed. llms.txt is a short, human-written guide to the pages that matter most, with context, aimed at AI systems.
Where do I put the file?
At the root of your domain so it loads at https://yourdomain/llms.txt, served as plain text (text/plain or text/markdown). On most hosts you upload it next to robots.txt; on site builders look for a custom-files or static-files setting.
My site isn't in English. Does that work?
Yes. We detect your page language and write descriptions in it by default, with localised section headings for Chinese, Japanese, Korean, Spanish, German, French and Portuguese (other languages get English headings). You can switch to English descriptions instead. The "## Optional" heading stays in English because the llms.txt proposal gives that exact heading a meaning.
How many links should llms.txt contain?
Enough to cover what people ask about you, usually 10 to 50. The draft caps itself at 40 and limits each section so one area doesn't crowd out the rest. Remove anything that isn't useful.
Is my content sent to an AI?
Yes, for this tool only: the titles, meta descriptions and link texts of your public pages, plus a short excerpt of your homepage text, are sent to Google Gemini to write the descriptions. Nothing else is sent, and nothing private, since we only read public pages.
Do you support llms-full.txt?
We read it when it's the only file you have, but we don't generate it yet.
Is it really free? Are there limits?
Yes, it's free and needs no account. To keep it fast for everyone, each visitor can run 6 checks per hour. If you hit the limit, the page tells you when you can try again.
Do you store the URL I check or the results?
No. The address and the results are only shown in your browser and are gone when you leave the page. To enforce the hourly limit we store a one-way hash of your IP address with a counter, nothing else. The llms.txt generator also sends public page titles and descriptions to Google Gemini, as explained above.
What does the full Cyberbard report add?
This tool checks one thing. The full report asks AI the questions your customers ask, shows which competitors it recommends instead of you, scores 50+ factors across your site and the wider web, and writes a Fix plan for your developer plus a Growth plan for the marketing side. You get 3 free reports when you sign up, with no card and no subscription.
More free GEO tools
AI Crawler Checker
Check whether GPTBot, ClaudeBot, PerplexityBot and 14 other AI and search crawlers can reach a page: robots.txt rules plus a live request with each bot's real user agent.
Open the toolSchema Checker for AI
See whether your structured data tells AI who you are: Organization and sameAs completeness, key fields per type, and ready-to-paste JSON-LD for what is missing.
Open the toolAI Citability Checker
Score any page paragraph by paragraph for how easily AI can quote it, with the reasons behind each score and what to change.
Open the toolLast updated