Free llms.txt generator
Enter a domain. We read your sitemap and up to 100 pages, and write the file from your own titles and descriptions. Then we check it against the spec and tell you which pages have no description to give.
- Free, no account.
- Up to 100 pages, about a minute.
- Nothing is stored.
What is llms.txt?
A short markdown file at the root of a website that tells AI models what the site is and which pages matter.
llms.txt (sometimes misspelled llm.txt) lives at yourdomain.com/llms.txt, next to robots.txt. Where robots.txt tells crawlers what they may fetch and a sitemap lists every URL, llms.txt is written for a language model: a map of the site in plain words, with the pages that answer real questions first.
The format was proposed by Jeremy Howard of Answer.AI in September 2024 and is documented at llmstxt.org. It is plain markdown, so a person can read it as easily as a model can.
- Titleline 1An H1 with the site's name. The only part the spec requires.
- Summaryline 3One line in a blockquote: what the site is, for whom. What an agent quotes when it has room for one sentence.
- Detailsline 5Free text without headings: anything a reader needs before the links.
- Sectionslines 7 to 17H2 headings with lists of links, one line each: the page, and what the reader finds there.
- Optionalline 19A section the spec reserves for pages an agent can skip when its context is short.
llms.txt example for acme.com
1# Acme2 3> Acme is invoicing software for freelancers: send invoices, track payments and chase late ones automatically.4 5Acme works in 30 currencies and connects to Stripe and PayPal.6 7## Product8 9- [Features](https://acme.com/features): Invoices, recurring billing, payment reminders and reports.10- [Pricing](https://acme.com/pricing): Free for 3 clients, $12 a month for unlimited.11 12## Docs13 14- [Getting started](https://acme.com/docs/start): Send your first invoice in five minutes.15- [API reference](https://acme.com/docs/api): REST endpoints for invoices, clients and payments.16 17## Optional18 19- [Changelog](https://acme.com/changelog): Every release since 2021.
How the llms.txt generator writes your file
From your own sitemap and your own page descriptions. Nothing is invented, so nothing in the file is wrong about you.
Sitemap: https://acme.com/sitemap.xml1Finds your pages
Reads robots.txt for the sitemap, then the sitemap and any sitemap index under it. Without a sitemap, the links on your home page.
<meta name="description" content="Send your first invoice in five minutes.">2Reads each page's own description
Up to 100 pages: the title, and the meta description or the first real paragraph. Pages marked noindex stay out.
## Docs - [Getting started](https://acme.com/docs/start): Send your first…3Writes and checks the file
Groups pages into sections by path, moves the long tail into Optional, and runs the result through the checker's structure tests.
How to publish the file
It lives at the root, next to robots.txt, and is served as plain text. How you get it there depends on what serves the site.
- 1.Save the file as llms.txt and upload it to the web root, next to robots.txt.
- 2.Make sure it is served as text/plain. Most hosts do that for .txt on their own.
- 3.Open it in a browser to confirm:
https://yourdomain.com/llms.txt
What llms.txt is for
It makes your site easy for an AI agent to read: one request, your structure, your words.
A map of the site in one request
An agent that has to learn a site page by page spends its time and context on navigation. With llms.txt it reads one short file, sees what is where, and fetches only the pages it needs.
Your words about your pages
Each page goes in with a line you wrote. A model summarising your site starts from what you said about it, not from whatever it picked out of the layout.
Clean markdown, not markup
A web page arrives wrapped in menus, scripts, cookie banners and footers. The file is the structure and the words, which is what a model reads best and cheapest.
Priorities, not everything
Sections put the pages that answer real questions first, and the Optional section tells an agent what it can leave out. A sitemap lists every URL; llms.txt says which ones matter.
Passes Lighthouse's agent audit
Lighthouse 13.3 added an Agentic Browsing category with an llms.txt audit, in PageSpeed Insights and Chrome DevTools. A valid file at the root is what it looks for.
A minute to make, nothing to run
It is a text file at the root of the site. Generate it, publish it next to robots.txt, and regenerate when the pages change. No script, no integration.
Frequently asked questions
A plain-text markdown file at /llms.txt that tells a language model what a site is and which pages matter: an H1 with the site's name, a one-line summary in a blockquote, then H2 sections listing pages as markdown links with a note each. Proposed by Jeremy Howard in September 2024 and documented at llmstxt.org.
llms.txt, with an s, at the root of the site: yourdomain.com/llms.txt. llm.txt is a common misspelling, and a file published under that name is one that tools and agents looking for llms.txt will not find. If you have one at /llm.txt, rename it or redirect it.
The site's name from the home page, its meta description as the summary, and one line per page: the page's title and its description. Pages are grouped by their first path segment, so /blog/* becomes a Blog section and /docs/* a Docs section, with root pages under Pages. A section past thirty links spills into an Optional section, which is what the spec provides for the part an agent may skip.
From robots.txt, which names the sitemap, and from the sitemap, including nested sitemap indexes. A site without a sitemap is read from the links on its home page. Up to 100 pages go into the file; past that, shallow pages come first and then the most recently changed, so the same site produces the same file twice.
Because the page has none: no meta description, no Open Graph description, and no paragraph long enough to stand in for one. We do not invent one. The generator lists those pages under the file so you can write descriptions on the site, which fixes the file and the pages at once.
No. Every line comes from the site's own titles and descriptions. A model would write a plausible sentence for a page it has skimmed, and a plausible sentence is what you least want next to your own name. It also keeps the tool free without a daily cap.
Because it is the cheapest way to make a site easy for an AI agent to read. One request gives the agent your own map of the site: what it is, which pages matter and what each one covers, in plain markdown instead of pages full of navigation and scripts. It takes a minute to generate, costs nothing to host, and passes Lighthouse's llms.txt audit.
Publishers include Stripe, Vercel and Mintlify on their main sites and Anthropic, OpenAI and Cloudflare on their developer docs, and an Ahrefs study of 137,000 domains in 2026 found a valid file on 28% of them. Readers are coding agents such as Claude Code and Cursor, documentation tools that load a product's docs into an agent, Lighthouse's Agentic Browsing audit, and SEO audit tools.
Google Search does not use it as a ranking signal, and Google has said so. The file is for a different reader: AI agents and assistants that read a site on someone's behalf. Google's own Lighthouse does check it, in the Agentic Browsing category added in version 13.3.
No. llms-full.txt is a convention rather than part of the spec, it runs to megabytes on a site of any size, and documentation platforms that need it generate it themselves. The checker notes whether you have one; the generator writes the index.
The generator reads the HTML the server sends, without running scripts, which is also what most crawlers do. A page whose title and description arrive only through JavaScript comes out with neither, and is listed among the pages with no description. That list is worth a look on its own: it is what a non-rendering reader sees of your site.
No. The pages are read for the request and the file is returned to you; nothing is written to a database and there is no account. Run it again after changing a description and the new file reflects the change.
The llms.txt checker reads the file a site serves and tests delivery, structure, links and robots.txt. The generator runs the same structure checks on the file it writes, so what you download has already passed them.
Other free tools
- Open tool
AI Visibility Checker
Check if ChatGPT, Gemini, Perplexity and Google AI name your brand, and get your AI visibility score.
- Open tool
AI Overview Checker
See if Google AI Overviews cite your site, which of your pages they pick, and who is cited instead.
- Open tool
Perplexity Visibility Tracker
Track whether Perplexity cites your site and names your brand in its answers.
- Open tool
ChatGPT Visibility Tracker
See if ChatGPT mentions your brand and where you rank in its answers.
- Open tool
Gemini Visibility Tracker
Check if Google Gemini mentions your brand and who it names instead.
- Open tool
Google AI Mode Visibility Tracker
See if Google AI Mode names your brand and which pages it cites.
- Open tool
Copilot Visibility Tracker
See if Microsoft Copilot mentions your brand and cites your site.
- Open tool
llms.txt Checker
See whether a site's llms.txt exists, follows the spec, has live links and is not blocked for AI crawlers.
- Open tool
robots.txt Generator
Create a robots.txt in a minute: block AI training, stay in AI search, add paths and your sitemap. Tested before you download it.
- Open tool
robots.txt Tester
Test any URL against robots.txt for Googlebot and 20+ AI crawlers, and find the line that decides each one.
- Open tool
AI Crawlers List
Every AI crawler with its user agent, IP list and robots.txt token, and whether your site lets each one in.
- Open tool
Google Search Console MCP
Ask Search Console in plain language from Claude, ChatGPT, Cursor or Claude Code. No Google Cloud project.
Next: see whether AI recommends you
llms.txt helps AI read your site. AskWatch shows what ChatGPT, Perplexity, Gemini and Google AI answer when buyers ask about your category, and who they name.
- Free, no credit card.
- Report in minutes, link sent to your email.