Schema Markup Generator
Build clean, valid Schema.org JSON-LD for rich results and AI answer engines — Article, Product, Local Business, FAQ, Event and more, with empty fields dropped automatically.
Build a clean, spec-compliant llms.txt — the curated file that tells ChatGPT, Claude and Perplexity which of your pages matter. Discover pages, keep the best, describe them, export
A curated llms.txt — the way the spec intends, not a dumped sitemap. Discover your pages, keep the 10–30 that matter, group and describe them, and export a file ChatGPT, Claude & Perplexity can actually read. Low-risk AI hygiene, done right.
# Your llms.txt preview will appear here
text/plain; charset=utf-8. Some hosts (Webflow, Framer, Shopify) serve it as HTML by default — confirm the content-type after upload.processed in your browser · never uploaded
Enter your site URL to auto-discover pages, or paste a list of URLs manually. Everything after this stays in your browser.
Copy the llms.txt or download it, then deploy it at your site root (yoursite.com/llms.txt), served as text/plain.
| Input | Output | Typical saving | Best for |
|---|---|---|---|
| your site URL | llms.txt | A whole site, discovered automatically from its sitemap | |
| a WordPress site | llms.txt | Pulling every published page and post from the WordPress REST API | |
| a pasted list of URLs | llms.txt | Curating by hand, or a site with no sitemap |
We ran the same files through the popular alternatives first. These are the gaps we found, and what this tool does instead.
The spec asks for a curated file. This helps you keep the 10–30 pages that matter and describe them, which is what AI tools actually use.
test: discover a large site and see the curation stepIt flags relative URLs and common mistakes before you export, so you don't ship a file AI crawlers ignore.
test: paste a relative URL and watch the warningIt tells you exactly where the file goes and the content-type it must be served as, including the hosts that get it wrong.
test: read the deploy note under the previewAn llms.txt file is a plain-text file at your site root that tells AI assistants — ChatGPT, Claude, Perplexity and Google’s AI Overviews — what your site is about and which pages matter. It’s the AI counterpart to robots.txt and your sitemap: robots.txt tells search crawlers what they may index, and llms.txt gives AI models a clear, curated map of your most important content so they can understand and cite it accurately. As answer engines replace some traditional search, it’s become a core piece of GEO/AEO (Generative / Answer Engine Optimization).
Here’s where most generators go wrong: they crawl your whole site and dump every URL into the file. But the llms.txt spec asks for the opposite — a curated file. This tool is built around that. It discovers your pages (from your sitemap, WordPress data or a live crawl), then helps you keep the 10–30 that genuinely matter, group them into sections, and add a one-line description for each — the format AI tools actually read. It also validates as you go, flagging relative URLs and common mistakes before you export.
Curation and export happen entirely in your browser; the only server step is the optional page-discovery, which reads your public sitemap. Prefer to keep it fully local? Paste your URLs manually instead. When you’re done, deploy the file at your site root so it’s reachable at yoursite.com/llms.txt, served as text/plain — a few hosts (Webflow, Framer, Shopify) serve it as HTML by default, so check the content-type after uploading.
One honest note: llms.txt is an emerging proposal, not a Google ranking factor — it won’t move your blue-link rankings and it can’t hurt them. It’s low-risk AI hygiene: a small, current step toward being represented accurately by the AI tools more people now search with.
A plain-text file at your site root that tells AI assistants like ChatGPT, Claude and Perplexity which pages on your site matter and what they're about — think of it as a curated guide for AI, in the spirit of robots.txt and sitemaps.
The llms.txt is built and downloaded entirely in your browser. The one exception is the optional "Discover pages" step, which sends your site URL to a helper service to read your public sitemap. Prefer to keep it fully local? Choose "paste URLs manually" instead.
At your site root, so it's reachable at yoursite.com/llms.txt, and served as text/plain. Some hosts (Webflow, Framer, Shopify) serve it as HTML by default — check the content-type after uploading.
The spec favours curation: keep the 10–30 pages that genuinely matter — docs, key products, important guides — rather than dumping every URL. A focused file is more useful to AI tools than an exhaustive one.
No. It's for AI assistants, not Google's search index, so it's low-risk AI hygiene rather than traditional SEO. It won't hurt your rankings and may help how AI tools represent your site.
Plain Markdown: an H1 with your site name, a short summary line, then sections (like Docs, Products or Guides) listing your key pages, each with a one-line description. This tool builds that structure for you and checks it against the spec before you export.
Publishing a clear, curated llms.txt at your root is one of the few concrete steps available today — it gives AI models a clean map of your important pages so they reference them accurately. Pair it with well-structured on-page content, since AI crawlers can't run JavaScript or navigate complex layouts.
Build clean, valid Schema.org JSON-LD for rich results and AI answer engines — Article, Product, Local Business, FAQ, Event and more, with empty fields dropped automatically.
Build a valid XML sitemap by discovering your pages automatically or pasting a URL list — with lastmod, priority, and automatic splitting for sites over 50,000 URLs.
Generate correct hreflang tags for multilingual and multi-region sites — as HTML link tags or an XML sitemap block — with validation that catches the mistakes Google flags.