Guides · Updated 2026-10-18

What is llms.txt? Format, examples and a free generator

llms.txt is a proposed standard (llmstxt.org) for a plain markdown file that gives large language models and AI agents a short, curated map of a website: what it is, and which pages matter most. The usual place is the root, /llms.txt. Think of it as a sitemap written for readers that have limited context windows.

The proposal is now at v2, updated in August 2026. It describes llms.txt as information an agent uses on demand while helping a user, rather than mainly as training data.

The format

The sections must come in this order:

  • An H1 with the name of the site or project (the only required part)
  • A blockquote with a short summary of the project
  • Optional markdown of any kind (paragraphs, lists) except headings
  • H2 sections containing "file lists": markdown lists where each item is a required link name, optionally followed by a colon and notes
  • By convention, a section named "Optional" for secondary links an agent can skip when it needs a shorter context

Example

# Acme Analytics

> Privacy-friendly product analytics for SaaS teams. Free up to 10k events/month.

## Docs
- [Quickstart](https://acme.com/docs/quickstart.md): install in 5 minutes
- [API reference](https://acme.com/docs/api.md)

## Product
- [Pricing](https://acme.com/pricing)
- [Acme vs Mixpanel](https://acme.com/compare/mixpanel)

## Optional
- [Changelog](https://acme.com/changelog)

Want real ones? We collected 300+ live llms.txt files from SaaS and AI companies on our llms.txt examples page. Check your own with the free llms.txt validator.

Root file or subpath files

In v2 the file can sit at the site root or at any path within it, and it covers the pages under that path: /docs/llms.txt covers everything in /docs/. When more than one file applies, agents should use the most specific one. The FastHTML project, for example, places its docs llms.txt at /docs/ to cover just the documentation pages.

Markdown versions of your pages

The proposal also suggests that pages agents might need have a clean markdown version at the same URL as the original page:

  • With .md appended: /docs/page.html becomes /docs/page.html.md
  • Or with the extension replaced: /docs/page.md
  • For URLs without a file name, append index.html.md or index.md

Help agents find the files

v2 recommends two standard link relations: rel="alternate" type="text/markdown" points to the markdown version of a page, and rel="describedby" points to the llms.txt file that covers it. You can add them as HTML <link> elements or as an HTTP Link response header. The header form also works for non-HTML files, such as the markdown files themselves, and can be set in your web server or CDN without touching the pages:

<link rel="alternate" type="text/markdown" href="/docs/page.html.md">
<link rel="describedby" href="/docs/llms.txt">

Link: </docs/page.html.md>; rel="alternate"; type="text/markdown", </docs/llms.txt>; rel="describedby"

llms-full.txt

Some sites also publish /llms-full.txt, which contains the actual text of the key pages in one file, so an agent can read everything in a single request. It is a common convention, not part of the llmstxt.org proposal.

Does it help?

llms.txt doesn't replace good HTML, crawler access or structured data. It's a low-effort addition that makes your site easier for agents and coding assistants to understand. According to the proposal, thousands of sites publish one, documentation platforms generate one automatically, Chrome's Lighthouse audits sites for one as part of its agentic browsing checks, and OpenAI, Anthropic and Gemini publish llms.txt files for their own developer docs.

Generate yours

RankRoot's free scan reads your homepage and drafts an llms.txt you can edit (llms.txt generator). The RankRoot Launch Kit ($79 once) includes 7 days of the full-site tools to audit up to 50 pages per scan and generate llms.txt, llms-full.txt and per-page JSON-LD, so you get both files for the whole site, and your product submitted to 100+ startup, SaaS and AI directories by our team within 7 days (with a proof report of every listing) and featured across RankRoot for 30 days (homepage, launch directory, your industry page and the tool AI agents use to find products).

Sources

Check your site now

Just your website. Free, no signup.

FAQ

Where do I put llms.txt?

Usually at the root of your domain, so it's reachable at https://yourdomain.com/llms.txt, served as plain text or markdown. The v2 proposal also allows files at subpaths, such as /docs/llms.txt, which cover the pages under that path; when several apply, agents should use the most specific one. You can point each page to the file that covers it with a rel="describedby" link.

Is llms.txt the same as robots.txt?

No. robots.txt tells automated tools which access to a site is acceptable. llms.txt is a content guide an agent reads on demand to learn what's important. You'll usually want both.

Do I need .md versions of my pages?

No, they're optional. The proposal suggests them for pages agents might need, at the same URL with .md appended (page.html.md) or the extension replaced (page.md), and index.html.md or index.md for URLs without a file name.

Do ChatGPT and Claude read llms.txt?

Support varies by product and changes over time. Agents and developer tools are the most common readers today. It's cheap to publish, so most sites that care about AI visibility add it.

How do I check my llms.txt is valid?

Run it through the free llms.txt validator. It checks the H1, summary, H2 link lists and Optional section, and can fetch a live file by URL, including one at a subpath.

More guides