llms.txt Generator

What is an llms.txt file?

An llms.txt file is a short Markdown file that tells an AI agent what a website is and where its important content lives. Web pages are built for people — navigation, ads and JavaScript wrap the information, and converting a page back into clean text is difficult and imprecise. An llms.txt file skips that work: it gives agents a concise, expert-level overview and a list of links to the pages that matter, in a format a program can parse with simple rules.

The idea was proposed by Jeremy Howard of Answer.AI in September 2024, and version 2 of the spec was published on 10 August 2026, after two years of real-world use. Thousands of sites now publish one, documentation platforms generate them automatically, and Chrome’s Lighthouse audits sites for one as part of its agentic browsing checks.

What llms.txt is — and what it is not

This is the honest part, and it matters. An llms.txt file does not make a site rank: Google has said Google Search ignores llms.txt, and it is not a ranking factor. It does not guarantee citations in AI answers either — in one 180-day test of ten sites, only two saw a measurable increase in AI-driven traffic, and Ahrefs found that 97% of the llms.txt files it tracked got zero requests.

What it does do is help the agents that choose to look. A coding agent fetching library documentation, or a chat assistant answering a question about a product, can start from your llms.txt instead of crawling your whole site. That is a real, modest benefit — and it costs almost nothing to provide. Build the file, check it, and then move on to the work that actually moves rankings: content, links and technical basics.

What is an llms.txt generator for, and who uses it?

The generator is for anyone who wants a correct file without memorising the spec: site owners, documentation teams, shop owners and bloggers. The file is used most heavily for software documentation, where coding agents follow it to find API references and tutorials. The same structure works anywhere an agent needs a guided path into a site’s content.

Documentation platforms such as Mintlify and GitBook generate an llms.txt file for every site they host. WordPress plugins including Yoast SEO and AIOSEO can generate one, Wix generates one for every site, and Shopify has served /llms.txt and /llms-full.txt on every store by default since 28 May 2026.

Benefits of a well-made llms.txt file

A correct file earns its place in four ways:

• A guided path for agents — instead of crawling everything, an agent starts from your curated list of the pages that matter.
• Smaller context, lower cost — the file itself stays small; the detail lives behind the links and is fetched only when needed.
• Fewer wrong answers — links with short descriptions help an agent judge which page to open, instead of guessing from URLs.
• Works alongside your other files — llms.txt complements robots.txt and your sitemap; it replaces neither. Robots.txt controls access, the sitemap lists everything for search engines, and llms.txt curates the overview for agents.

The v2 format, line by line

The file follows a specific order. An optional byte-order mark may come first, then an H1 with the name of the project or site — the only required part. Next comes a blockquote (lines starting with >) with a short summary of the project. After that, zero or more detail sections of any Markdown except headings, and then zero or more H2 sections containing file lists.

Each file-list line looks like this: “- [Link title](https://example.com/page.md): a short description of the page.” The link is required; the description after the colon is optional but recommended. An H2 section named “Optional” is, by convention, for secondary links an agent can skip when it needs a shorter context.

How to generate your llms.txt file

Use the generator above: add your site name and summary, then add sections and links — or paste your sitemap.xml to pre-fill titles and URLs. Write a one-line description for every link, then copy or download the file and save it as llms.txt in your site’s root folder.

When the file is live, open example.com/llms.txt in a browser to confirm it loads as plain text, then run it through our llms.txt Checker to confirm it follows the v2 spec.

Best practices — and common mistakes

Most llms.txt problems come from a short list of avoidable errors:

• Put the H1 title first — it is the only required part, and it must be line one. A file without it is not a valid llms.txt.
• Use absolute URLs starting with https:// — relative links cannot be followed from outside your site.
• Give every link a short description after the colon, so agents can judge whether to open it.
• Keep the file small — detail belongs in the linked pages, not in the overview.
• Do not put private or sensitive information in the file — it is public, and anyone can read it.
• Do not expect Google to read it — Google Search ignores llms.txt. The file is for AI agents that look for it, not for rankings.