Free tool · AI crawler guidance

llms.txt Generator

Create an llms.txt file so ChatGPT, Claude, Gemini, and other AI systems can prioritize your best pages. Auto-discover from your sitemap, organize sections, and download your llms.txt for free.

llms.txt feeds your site summary to ChatGPT Search, Claude (Anthropic), Perplexity AI, Google Gemini llms.txt

No account needed · Free builder · Manual entry supported · Automatic sitemap discovery up to 30/day

Improve with the AEO toolkit

After you publish llms.txt, score key pages and fill content gaps so AI systems have more to cite.

Simple process

How to generate your llms.txt

  1. Enter your site name & summary

    Add your site or product name and a one-line description. This becomes the title and quote block at the top of your file.

  2. Auto-discover pages (optional)

    Enter your domain and the tool scans your sitemap.xml, grouping URLs by section automatically. No sitemap? Add links manually instead.

  3. Organize into sections

    Group links under clear headings — Docs, Guides, Pricing, API Reference — the same way you would organize a table of contents.

  4. Download & upload

    Copy or download the generated llms.txt, then upload it to your site root so it's reachable at yoursite.com/llms.txt.

What is llms.txt and why does it matter?

An optional markdown guide at your site root that summarizes your site and priority pages for systems that choose to use the proposed convention.

Definition

llms.txt is a proposed plain-text file placed at a site root to summarize the site, its intended audience, and selected priority links in a markdown-friendly format. It offers optional guidance to systems that choose to read it; it is not an access-control standard, a replacement for robots.txt or sitemaps, or a guarantee of crawling, ranking, citation, or AI use.

Some AI-assisted search products fetch and cite live web pages at query time. robots.txt controls crawler access; llms.txt is a separate, proposed convention for summarizing core docs, pricing, and key guides in a concise text format. Support varies, so treat the file as optional guidance rather than an access rule or ranking signal.

Adoption is still early and varies by product. A concise, maintained file can still serve as a useful machine-readable directory and editorial inventory, but publishers should evaluate it as an experiment and keep canonical pages, sitemaps, structured data, and crawl controls authoritative.

What a good llms.txt includes

Four pillars that separate a useful file from a dump of every URL on your site.

Clear identity

  • Site or product name as H1
  • One-line summary as a quote block
  • No marketing fluff — direct, factual description

Organized sections

  • Logical grouping (Docs, Guides, API, Pricing)
  • Short labels, not full sentences
  • Optional one-line notes per link

Curated, not exhaustive

  • Your most important pages, not every URL on the site
  • Prioritize docs, guides, and canonical reference pages
  • Skip low-value pages (legal, archived content, thin tag pages)

Kept current

  • Update when you add major docs or restructure sections
  • Treat it like a sitemap for humans-reading-as-AI, not a one-time file

llms.txt vs. robots.txt vs. sitemap.xml

Three root files, three audiences — don’t confuse access rules with a curated AI summary.

These three files sound similar but serve different audiences. Confusing them is the most common mistake when adding llms.txt for the first time.

Comparison of robots.txt, sitemap.xml, and llms.txt
robots.txt sitemap.xml llms.txt
Audience Search crawlers Search engines AI systems / LLMs
Purpose Access rules Full URL list Curated summary
Format Directives XML Markdown
Required? Best practice Best practice Emerging convention

Methodology & limitations

  1. Optional discovery fetches only public, same-origin robots.txt and sitemap resources through the shared SSRF-safe fetch layer; private and unsafe network targets are blocked.
  2. Sitemap discovery is bounded: the generator samples a limited number of same-origin child sitemaps and returns at most 200 URLs for review rather than treating every discovered page as important.
  3. You remain the editor. Remove utility, duplicate, private, thin, or outdated URLs and describe the site accurately before publishing the generated file.
  4. llms.txt is a proposed convention with varying adoption. A valid file does not control crawler access and cannot guarantee discovery, ranking, citation, summarization, or use by any AI product.

Frequently asked questions

Quick answers about format, placement, and how AI systems use the file.

What is llms.txt?
llms.txt is a proposed plain-text file at your site root that summarizes what your site is about and which pages matter most. It helps AI systems — when they choose to use the convention — find documentation, pricing, and key guides faster than crawling every URL.
Who uses llms.txt?
Support varies by product and changes over time. Teams publish llms.txt as optional guidance for AI crawlers and assistants such as ChatGPT, Claude, Gemini, and other LLM-based tools — not as a required search-engine standard like robots.txt.
Is llms.txt an official web standard?
Not yet in the way robots.txt or sitemap.xml are. It's a proposed, community-driven convention that several AI companies and tools have started supporting. Adding one costs little and may help AI systems summarize your site more accurately — but it is not something search engines currently require.
Does llms.txt replace robots.txt or sitemap.xml?
No. robots.txt controls crawler access; sitemap.xml lists URLs for discovery. llms.txt is a separate, curated summary for AI-oriented readers. Keep all three when they serve different jobs.
Where do I upload the generated file?
To your site's root directory, so it's reachable at yoursite.com/llms.txt — the same location as robots.txt. On WordPress, this usually means uploading via FTP/SFTP or a plugin that allows root-level file uploads, since the file must sit outside the /wp-content/ folder.
What pages should I include?
Your most important, evergreen content: documentation, core guides, pricing, and any page you'd want an AI system to reference first. Avoid listing every URL on your site — llms.txt works best as a curated summary, not a full sitemap duplicate.
Does sitemap auto-discovery work on every site?
It requires a reachable sitemap.xml (or one referenced in robots.txt). If neither exists, the tool falls back to manual entry — you can still build a complete file by adding sections and links by hand.
How often should I update llms.txt?
Whenever your priority pages change — new docs, pricing, or cornerstone guides. A stale file is still better than none, but a short quarterly review keeps the guide useful for AI systems.
Will this improve my Google rankings?
No — llms.txt has no confirmed effect on classic Google, Bing, or Yandex rankings. It's aimed specifically at how AI systems parse and cite your site, which is a separate (though related) goal from traditional SEO.
How is this different from the AEO Readiness Checker?
The AEO Readiness Checker scores measurable on-page signals such as schema, headings, and trust. This tool creates an optional site-level content guide under the proposed llms.txt convention; it does not score pages or guarantee crawler use.

Why trust this llms.txt generator?

Same SSRF-safe tooling as our AEO checker — built for production sites, not a generic form wrapper.

Built by Maksut as part of the same AEO tooling behind the AEO Readiness Checker and AI Content Gap Finder — production WordPress and technical AEO work, not a generic form wrapper. Sitemap discovery uses the same SSRF-safe fetch infrastructure as the other tools on this site, so scanning your domain is safe by default.

llms.txt is an emerging, unofficial convention — no vendor guarantees it will be used, and adoption varies by AI provider. This tool helps you ship a correctly-formatted file quickly; it does not promise a specific outcome in any AI system's answers.