01.
Edit the draft
Rewrite the summary line in plain words, fix titles that read badly, and remove pages a buyer would never need.
Free llms.txt Generator: Give AI a map of your website.
Enter your domain. The generator reads your homepage, sitemap, and key pages, then writes an llms.txt file you can edit, copy, and publish in a few minutes.
- No signup
- Reads your sitemap
- Edit before you publish
Generate your file.
Paste your website. The file is ready in under a minute, no email required.
What is llms.txt
A short markdown file
that maps your site for AI.
llms.txt is a proposed standard: a plain text file at the root of a website that tells language models what the site is and which pages are worth reading.
01
Name and summary
An H1 with the site name, then a one-line blockquote that says what the company does and who it is for.
02
Sections of links
H2 sections such as Products, Docs, or Customers, each a list of links with a short note on what the page answers.
03
An Optional section
Blog posts, legal pages, and other material a model can skip when it has limited room to read.
What a good
llms.txt looks like.
Short, specific, and current. Every link says what the page answers, so a model can pick the right one without opening them all.
# Acme
> Acme is invoicing software for B2B SaaS finance teams that bill on usage.
## Main pages
- [Home](https://acme.com/): Usage-based invoicing for B2B SaaS.
- [Pricing](https://acme.com/pricing): Plans, limits, and annual terms.
## Docs
- [API reference](https://acme.com/docs/api): Endpoints, auth, and webhooks.
## Optional
- [Blog](https://acme.com/blog): Billing operations guides.How to add it
Four steps
from draft to live.
The generator writes the draft. Publishing takes a few minutes on most stacks.
02.
Save it at the root
Publish it as plain UTF-8 text at yourdomain.com/llms.txt. On Next.js, put it in the public folder. On WordPress, upload it to the site root or use an SEO plugin that manages llms.txt.
03.
Check that it loads
Open the URL in a private window. It should return the raw text, not an HTML page or a redirect to the homepage.
04.
Keep it current
Regenerate or edit it when you launch, rename, or retire important pages, so the file never points at dead links.
What llms.txt
will not do.
None of the major answer engines has said it uses llms.txt to choose which sources to cite. Some AI tools and agents do read it, especially coding assistants and documentation tools, and it costs very little to publish.
Treat it as a tidy index, not a ranking lever. Whether ChatGPT, Perplexity, or Google AI cite you still depends on crawl access, pages that answer buyer questions directly, and proof they can trust.
FAQ
llms.txt questions.
What the file is, where it goes, and how much it matters.
llms.txt is a proposed standard for a plain markdown file at the root of a website, at /llms.txt. It gives language models a short summary of the site and a curated list of the pages worth reading, grouped into sections, so they do not have to work it out from navigation and HTML.
It reads your homepage, robots.txt, sitemap, and up to 40 public pages on your domain, then writes a draft llms.txt with your site name, a summary line, and links grouped into sections such as Products, Docs, Customers, and Company. Blog and legal pages go under Optional. You can edit the draft, copy it, or download it.
Not as a confirmed ranking or citation signal. None of the major answer engines has said it uses llms.txt to choose sources. Some AI tools and agents do read it, especially coding assistants and documentation tools. It is cheap to publish, but crawl access, clear pages, and proof matter far more for AI visibility.
At the root of your domain, so it loads at yourdomain.com/llms.txt as plain text. On Next.js, place it in the public folder. On WordPress, upload it to the site root or use an SEO plugin that manages llms.txt. Check that the URL returns the raw text rather than an HTML page.
robots.txt tells crawlers what they may and may not fetch. llms.txt does not grant or block access; it points models at the pages that best explain the site. You need robots.txt to allow AI crawlers before llms.txt can help at all.
llms-full.txt is a companion file some sites publish with the full text of their key pages in one document, mostly for documentation. This generator creates llms.txt, the index file. Most marketing sites only need llms.txt.
Yes. There is no signup and no email gate. A light hourly limit per visitor keeps the crawler from being abused, and results for the same domain are cached for an hour.
Yes. The generator works from your page titles and meta descriptions, so the draft is only as clear as those are. Rewrite the summary line in plain words, fix vague titles, and remove pages you would not send a buyer to.
No. It is a small, optional signal. Answer engines still need to crawl your pages, understand the offer, and find proof they can trust. The free AEO checker shows where those gaps are, and Raze's AEO service fixes them.