Help AI understand
your whole site.
Enter your domain and we'll map your pages into an llms.txt in the llmstxt.org format: one plain-text file that tells AI tools what your site is and where its key pages are. Free.
What you'll walk away with.
A clean, structured map of your site that AI models can read in one file.
# Acme > Project tools for small teams ## Product - [Features](/features) - [Pricing](/pricing)
A ready-to-use file
Valid llms.txt in the llmstxt.org format, with your site name, summary and page links.
Grouped by section
Your pages sorted into Documentation, Product, Blog and Company, with everything else under Optional.
Built for AI readers
A clean map of your site for the assistants that increasingly answer for your brand.
Make your site easy for AI to read.
AI assistants have to make sense of your site from raw HTML and JavaScript. An llms.txt hands them a clean, plain-text map instead, so they get you right.
<div class="hero"><nav>…</nav> <script>…</script> <div id="app" data-… > <span class="c-1x">…</span> </div></div>
AI has to guess your structure from tangled markup and JavaScript.
# Acme > Project tools for small teams ## Product - [Features](/features) - [Pricing](/pricing) ## Docs - [Getting Started](/docs)
One clean file: what you are, and where everything important lives.
Speak the AI's language
A single, clean file tells assistants what your site is and where the important pages live, instead of leaving them to guess from messy HTML.
Generated in seconds
We read your robots.txt and sitemaps and build the whole file for you, no manual page-by-page writing.
Works on any site
Blogs, SaaS, docs, e-commerce: if it has a sitemap, we can map it into an llms.txt in the llmstxt.org format.
One domain in, a clean map out.
No manual writing, no schema to learn. Paste a URL and copy the file.
Enter your domain
Any public site, no setup or install.
Paste any public website URL. We read its robots.txt and sitemaps to discover the pages that matter.
We map your pages
Your pages are sorted into sections automatically: Documentation, Product, Blog, Company and Optional.
Copy or download
# Acme > Project tools for teams ## Product - [Features](/features) - [Pricing](/pricing)
Get a ready-to-use llms.txt in seconds. Review it, then drop it at your site root.
Understanding llms.txt.
What the file is, what goes in it, what it can and can't do, and how to publish it.
What llms.txt is
llms.txt is a proposal published at llmstxt.org by Jeremy Howard in September 2024, with a second version in 2026. It's a single markdown file at your site root that tells large language models what your site is and where its important pages are: a short, curated, plain-text map instead of raw HTML, navigation and scripts.
It's a proposal, not an official web standard. No standards body has adopted it, and no AI provider is obliged to read it. Treat it as a cheap, low-risk addition, not a ranking factor.
The llms.txt format, part by part
The spec defines a fixed order. Only the first part is required; everything else is optional, but a useful file has all of it.
- H1 title (required)
- One line starting with "# " and the name of your site or project. This is the only part the spec requires.
- Blockquote summary
- A line starting with "> " that says in a sentence or two what the site is and who it's for. It's the first thing a model reads, so make it specific.
- Details
- Optional paragraphs or lists after the summary, with no headings. Use them for context a model would otherwise get wrong, such as what you don't do or which product name replaced an old one.
- H2 sections (file lists)
- Headings starting with "## " that group your links, such as Docs, Product or Blog. The spec doesn't fix the section names; pick the ones that describe your site.
- Link entries
- Each item is a markdown link, [Page name](https://yoursite.com/page), optionally followed by a colon and a short note about what the page covers.
- The Optional section
- An H2 named exactly "Optional" has a special meaning: it holds secondary links an AI tool can skip when it needs a shorter context. Don't put pages you care about there.
What this generator puts in your file
It builds a first draft from your sitemap and homepage. Knowing exactly what it does tells you what to check before you publish.
- Site name
- Taken from your homepage title tag, or from your domain if the page has no title.
- Summary
- Your homepage meta description (or Open Graph description), used word for word. If your homepage has neither, the file has no summary, so write one.
- Pages
- Read from your sitemap, up to 120 URLs in the order the sitemap lists them. With no sitemap, it checks common paths like /pricing, /docs and /about instead. The homepage itself is left out of the list.
- Sections
- Pages are sorted by URL pattern into Documentation, Product, Blog and Company. Legal pages and anything that doesn't match a pattern go under Optional, so on many sites your main service or product pages land there. Move them up before publishing.
- Link names
- Built from each URL's last segment, so /pricing-plans becomes "Pricing Plans". It doesn't read each page, so it doesn't write the optional notes after each link. Add a short note to the pages that matter most.
- Long sections
- Each section shows up to 20 links, then a line saying how many more were found. Replace that line with the pages you actually want listed, or delete it.
llms.txt vs robots.txt vs sitemap.xml
All three sit at your site root, and they do different jobs. llms.txt doesn't replace either of the others.
- robots.txt
- Access rules for crawlers: which bots may fetch which paths. Blocking or allowing AI crawlers like GPTBot happens here, not in llms.txt.
- sitemap.xml
- A complete list of the indexable pages on your site, in XML, for search engines to discover and recrawl.
- llms.txt
- A short, hand-picked list in markdown, with a summary and notes, for language models to read. A curated shortlist, not a full index.
What about llms-full.txt?
llms-full.txt is a companion file some documentation platforms publish: the full text of your pages in one markdown file, rather than links to them. It isn't part of the llmstxt.org spec. It's a convention that grew up around developer docs, where a coding assistant can load a whole manual in one request. It can be very large, and it goes stale every time a page changes.
This generator makes llms.txt only, not llms-full.txt. For most business sites, llms.txt is the one to start with. If you run a docs site, check whether your docs platform can export llms-full.txt for you.
Version 2 of the spec adds two related ideas: a clean markdown copy of each page at the same URL with .md on the end, and extra llms.txt files in subfolders (such as /docs/llms.txt), each covering the pages under its path. Both are optional.
Does llms.txt help SEO or AI citations?
Honestly, nobody can show that it does yet. No major AI company has confirmed that its assistant reads llms.txt when deciding what to cite, and Google has said you don't need it, or any other special file, to appear in AI Overviews or AI Mode. It has no effect on traditional Google rankings.
Where it does get used is on request: coding agents and AI tools fetch a site's llms.txt when a person points them at it, and several AI companies publish one for their own developer docs. So it's worth the ten minutes it takes, but it won't get you recommended on its own. What drives AI citations is the same as what drives rankings: pages that answer the question clearly, and other sites mentioning you. To see whether AI tools already mention you, try the free AI visibility checker.
How to publish and maintain it
Put the file at your root so it resolves at yoursite.com/llms.txt, served as plain text. Where it goes depends on your setup: the public folder in Next.js, Astro or Nuxt, the site root (often public_html) on WordPress or cPanel hosting, or the root of your static host. Some platforms and WordPress SEO plugins can create one for you. Platforms that don't let you upload to the root may need a redirect from /llms.txt to a file you host elsewhere.
- 1Move your main product or service pages out of Optional
- 2Drop links you don't want featured and add any key page that's missing
- 3Rewrite the summary in your own clear words
- 4Add a short note after the links that matter most
- 5Upload the file to your site root as /llms.txt
- 6Open yoursite.com/llms.txt in a browser and check it shows as plain text, not a 404 or an HTML page
- 7Regenerate or edit it when you add or restructure sections
Common llms.txt mistakes
Most problems come from treating the file like a sitemap or an ad.
- Listing every page
- The point is curation. A file with hundreds of links tells a model nothing about which ones matter. Aim for your key pages, not your archive.
- Broken or redirected links
- Every link should load a live page. Check after you remove or rename pages.
- Pages blocked in robots.txt
- Listing a page you block crawlers from sends a mixed signal. Keep the two files consistent.
- A marketing summary
- "The world's leading platform" tells a model nothing. Say what you do, for whom, and where.
- Wrong place or format
- It has to be at /llms.txt (not /llms.txt.html or a page in your CMS) and readable as plain text.
- Set and forget
- An old file pointing at retired pages is worse than none. Update it when your site changes, and check it every few months.
Or let your agent do it for you
This tool is one check. SEOLadders is an AI SEO agent that runs the whole job on your site, every day.
Tracked on six AI engines
It tracks whether ChatGPT, Perplexity, Gemini, Claude, Google AI Overview and Google AI Mode recommend you, rechecked throughout the week.
Keyword research and topic clusters
It finds what your customers search for, groups it into topic clusters around pillar keywords, and plans the articles that cover them.
30 articles a month, published
It writes and publishes 30 articles a month to your site, with images, citations and links. Auto-publish is on once your CMS is connected; turn on Review mode to approve each one.
Backlink outreach, drafted
It finds link targets and drafts the outreach for you to send from your own inbox. The link exchange places links inside members' articles.
A site audit with fix steps
It audits your site and lists what to fix, with steps written for the platform your site runs on. Content Radar spots pages losing clicks.
3-day free trial. Cancel anytime, no charge, no questions.
More free tools.
The rest of the toolkit, free to use right now.
AI Visibility Checker
See how often ChatGPT and Google's AI mention your brand, and who they name instead.
Try freeAI Overviews & AI Mode Checker
See Google's AI Overview and AI Mode answers for any keyword, every source they cite, and whether you're one.
Try freeSERP Checker
See Google's live top 10 for any keyword in any country, plus AI Overviews and People Also Ask.
Try freeKeyword Rank Checker
Check where your site ranks on Google for any keyword, which page ranks, and who's above you.
Try freeKeyword Difficulty Checker
Get a 0–100 difficulty score, monthly search volume and intent for any keyword before you write.
Try freeSEO Audit
Crawl up to 50 pages and find the technical and on-page issues holding your site back.
Try freeLLMs.txt Generator, answered.
What it does, what it runs on, and how it fits the platform.
See the full platform →llms.txt is a proposal from llmstxt.org: a single markdown file at your site root that tells large language models what your site is and where its important pages are. It's a curated, plain-text map for AI readers, similar in spirit to robots.txt and sitemap.xml but written for models.
Rank on Google and get cited
by AI on autopilot
Connect your site once and the work runs in the background, it finds the topics, builds the content and authority behind them, then tracks where you land on Google and how often AI platforms recommend you.