XML sitemap, llms.txt, and markdown generator

Free XML sitemap generator. llms.txt and markdown from one crawl.

XML sitemap, llms.txt, and clean markdown — produced from a single crawl of your site.

Free. Includes llms.txt + standard XML. No credit card.

Optimized for these AI platforms

ChatGPTClaudePerplexityGoogleGeminiBing

All product names, logos, and brands are property of their respective owners. Not affiliated with or endorsed by OpenAI, Anthropic, Perplexity, Google, or Microsoft.

How it works

From URL to three files in one crawl.

No installs, no configuration. Paste a URL and we hand back a sitemap, an llms.txt, and a markdown bundle.

1

Paste your URL

Drop in any domain — root, subdomain, deep page. No login required for your first crawl.

2

We crawl every page

Our crawler discovers every linked page, renders JavaScript when needed, and respects robots.txt.

3

Download your files

Pick the format you need. XML for search engines, llms.txt for a curated site index, HTML for visitors, and markdown for LLM and RAG workflows.

A complete XML sitemap, generated in seconds.

Your sitemap.xml is how Google, Bing, and every other search engine discover your pages. Sitemap.ai writes a clean, valid one for you — ready to submit.

sitemap.xml
<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
  <url>
    <loc>https://yoursite.com/</loc>
    <lastmod>2026-05-30</lastmod>
    <changefreq>weekly</changefreq>
    <priority>1.0</priority>
  </url>
  <url>
    <loc>https://yoursite.com/about</loc>
    <lastmod>2026-05-12</lastmod>
  </url>
  <!-- + 1,498 more URLs -->
</urlset>
Ready to submit to Google Search Console and Bing Webmaster Tools.

Every URL. Every update. Indexed faster.

A sitemap.xml file maps your site structure for search engines — which pages exist, when each was last modified, how often they change. The result: new pages get indexed faster, important pages don't get missed, and you control which URLs Google sees.

We handle the details. Required tags, optional SEO metadata, and an automatic sitemap index when you cross 50,000 URLs. No hand-coded XML. No plugins. Submit it to Google Search Console and you're done.

A readable index for AI and developer workflows.

Publish a site summary and curated links in Markdown for tools that support the llms.txt proposal.

Weekly active LLM users
2023 — 2026
Example trend; not measured user or referral data.
1B750M500M250M2023202420252026~1B today
Public usage figures from OpenAI, Anthropic, Perplexity.

AI search isn't a side channel anymore.

AI search can surface useful pages as sources. Keep your content accessible, accurate, and clearly structured; publishing llms.txt alone does not guarantee a citation.

llms.txt is an emerging Markdown proposal for publishing a site summary and curated page links. It can help tools that support the format understand your content, but it does not replace robots.txt or an XML sitemap, and it does not guarantee AI search visibility or citations.

Markdown files — the format LLMs really want.

Export every crawled page as clean markdown. Drag the folder into a chat, feed it into a RAG pipeline, or use it as a portable archive of your site.

stripe-com-markdown.zip
5 files
manifest.json2.1 KB
Click a file to preview its markdown. One file per crawled page.

Hand your entire site to ChatGPT, Claude, and Gemini.

XML is for crawlers. Markdown is for the models themselves. We extract the main content of every crawled page — stripping nav, footer, ads, and tracking scripts — and emit one clean .md file per URL.

Drop the zip into a ChatGPT, Claude, or Gemini conversation. Feed it into your own embedding pipeline. Keep it as a snapshot of your site. Same crawl that builds your sitemap, no extra steps.

One crawl, multiple export formats.

Sitemap.ai crawls websites and produces XML sitemaps, an optional llms.txt site index, and clean per-page markdown.

XML sitemaps help search engines discover your URLs. llms.txt provides an optional site index, and clean markdown is useful for LLM and RAG workflows. Sitemap.ai produces all three from a single crawl.

stripe.com
Crawl complete
Ready
4,328
URLs found
2m 14s
Crawl time
99.8%
200 OK
Download
Benefits

The full toolkit, from one tool.

Every crawl does more than generate files — it makes your site easier to find, easier to cite, and easier to fix.

Stronger Technical SEO

A current sitemap helps search engines discover new and deeply nested pages. Indexing is not guaranteed. Submit it to Search Console, then re-crawl anytime you publish to regenerate it.

Better AI Visibility

Give supported AI tools a readable site index and clean markdown for LLM and RAG workflows. Search visibility still depends on accessible pages, useful content, and each platform's indexing and retrieval systems.

Track Every Site

Save crawls as projects, watch them run live, and re-crawl in one click after you publish. A free account covers 5,000 URLs per crawl and 50,000 per month — no credit card required.

Scheduled Crawls

Set your projects to re-crawl automatically — daily, weekly, every two weeks, or monthly. Each run happens on our servers and emails you (or pings Slack) when it’s done, so your sitemap and llms.txt stay current without you lifting a finger. Free with an account.

Compare Crawls

See URLs added, removed, unchanged, or reformatted between any two completed crawls. Git-style reports, sampling safeguards, filters, and CSV exports make site changes easy to verify.

Crawl 10× more URLs with a completely free account. Sign up today.

5,000 URLs per crawl. 50,000 URLs per month. JavaScript rendering. XML, llms.txt, and markdown exports from every crawl.

20-second signup. No credit card required.

XML + llms.txt
Both files, one crawl
5,000 URLs / crawl
10× the guest limit
Save & re-crawl
One click to refresh

FAQ

What is an XML sitemap?

An XML sitemap is a structured XML file — typically named sitemap.xml — that lists the important URLs on your website along with metadata like the last modified date and how often each page changes. Search engines use it to discover and index your pages faster, especially on large websites or sites where internal linking is sparse.

How does an XML sitemap generator work?

A sitemap generator crawls your website by following internal links from your homepage outward, discovering every reachable URL. For each valid page it records the URL, last modified date, and (optionally) priority and change frequency, then writes everything into a single sitemap.xml file. Generators automatically exclude duplicate content and utility pages, and if your site exceeds 50,000 URLs the tool will split output into multiple files indexed by a sitemap index file — no XML hand-coding required.

How do I submit a sitemap to Google?

Upload the generated sitemap.xml to the root of your website (e.g. yoursite.com/sitemap.xml), then open Google Search Console, choose your property, go to Sitemaps, paste the URL, and click Submit. Bing accepts the same file via Bing Webmaster Tools. After submission, search engines will recrawl the file periodically and pick up new pages automatically — just regenerate and re-upload after major content changes.

What's llms.txt?

llms.txt is an emerging Markdown proposal for publishing a site summary and curated links. Support varies by tool. It does not control crawler access or guarantee indexing, rankings, or citations. Keep robots.txt and your XML sitemap too; Sitemap.ai generates llms.txt alongside standard XML.

What's the difference between a sitemap and a sitemap index file?

A single sitemap.xml file can contain up to 50,000 URLs and must be under 50MB uncompressed. Once your website scales past either limit, the generator produces multiple smaller sitemap files plus a sitemap index — one master XML file that lists all the individual sitemaps. You submit the index URL to Google Search Console and it handles the rest. Sitemap.ai builds the index automatically when you cross the threshold.

Does this work with WordPress, Shopify, Webflow, and other CMSs?

Yes — Sitemap.ai works with every major CMS and platform, including WordPress, Shopify, BigCommerce, Webflow, Squarespace, Wix, Ghost, HubSpot, Framer, and custom-built sites. We crawl the live URL the same way Google does, so it doesn't matter what's under the hood. No plugin install, no dashboard access, no Yoast or platform-specific SEO addon required. You get a clean sitemap.xml plus llms.txt for AI crawlers from a single crawl — and you can re-run it anytime after publishing new content.

How does this compare to Screaming Frog?

Screaming Frog is a desktop app you install on your computer — it's powerful for SEO audits but capped at 500 URLs on the free tier, and crawl speed is limited by your laptop. Sitemap.ai runs in the cloud, so you can crawl from any device, get 5,000 URLs free, and schedule automatic re-crawls that keep your sitemap current without you lifting a finger.

Does this replace my Google sitemap?

No — it complements it. You get standard XML for Google + Bing, llms.txt for AI crawlers, and a per-page markdown bundle for LLM and RAG workflows. One crawl, every file.

Which AI bots are supported?

Our AI Crawler Checker evaluates robots.txt rules for OAI-SearchBot, GPTBot, ChatGPT-User, and other published crawler tokens. OAI-SearchBot supports ChatGPT search; GPTBot controls potential training use. The checker reports public policy, but does not change your robots.txt or guarantee that firewalls allow a real crawler.

Is it really free?

Yes. 500 URLs as guest, 5,000 URLs per crawl + 50,000/month + JS rendering with a free account. No credit card.

Do I need an account?

No, but signing up for a free account (no credit card required) unlocks JavaScript rendering and lets you save your crawls and re-run them anytime. You also get 50,000 URLs per month and can crawl up to 5,000 URLs per crawl.

Can I keep my sitemap automatically updated?

Yes. Create a free account, save your site as a project, and set it to re-crawl on a schedule — daily, weekly, every two weeks, or monthly. Each run happens automatically on our servers, regenerates your sitemap, llms.txt, and markdown, and emails you when it’s done. No need to remember to re-crawl after you publish.

Can you crawl React / Next.js sites?

Yes — toggle on JavaScript rendering (free with account). Real Chromium under the hood catches every client-side route.