llms.txt Generator
Enter your site name, a short summary and the pages you want AI assistants to find, grouped into sections, and the tool writes an llms.txt Markdown file you can copy or download. llms.txt is a community proposal from llmstxt.org, not an official standard, and publishing one does not guarantee that any AI product will use it or that your visibility or rankings will change.
Runs in your browser
Free, no sign-up. The file is built in your browser. Nothing you type is uploaded, stored or sent to analytics.
Site details
Optional links
Secondary pages an assistant can skip when it needs a shorter context. Written under an "Optional" heading.
llms.txt
- Site or project name is required (it becomes the H1).
- No links yet. An llms.txt with only a title gives assistants nothing to follow.
Save as llms.txt and serve it from your site root (/llms.txt). llms.txt is a community proposal, not a standard, and it does not guarantee AI visibility or rankings.
How to use the llms.txt Generator
- Type your site or project name (required). It becomes the H1.
- Add a one or two sentence summary and, if useful, extra notes in Markdown.
- Create sections such as Docs or Products. Add links with a title, a full http(s) URL and a short description.
- Put lower-priority pages in the Optional links box. They are written under an Optional heading.
- Fix any errors shown above the preview, then press Copy or Download.
- Save the file as llms.txt and publish it at the root of your site, for example https://example.com/llms.txt.
Worked example
Sample data
Name: Acme Docs Summary: Docs for Acme. Section Docs: Quickstart, https://acme.example/quickstart, Get started in 5 minutes Optional: Changelog, https://acme.example/changelog
# Acme Docs > Docs for Acme. ## Docs - [Quickstart](https://acme.example/quickstart): Get started in 5 minutes ## Optional - [Changelog](https://acme.example/changelog)
Links without a description are written without the colon part. Empty links and sections are left out.
How it works
What llms.txt is
llms.txt is a proposal published at llmstxt.org: a Markdown file at /llms.txt that gives language models a short, curated map of a site, so they can find the most useful pages without parsing a full HTML site.
It is a community proposal, not an IETF, W3C or other formal standard. Support varies by AI product and may change, and no vendor has to read the file. It does not control access (that is robots.txt) and it does not guarantee citations, traffic or rankings.
The format this tool writes
An H1 with the site name, an optional blockquote summary, optional free-form notes, then H2 sections that each contain a bullet list of Markdown links with an optional colon and description. A section named Optional marks secondary links that can be skipped when context is short.
# Name > Summary ## Section - [Title](https://url): description ## Optional - [Title](https://url)
What the tool does not do
It does not crawl your site or fetch any URL. This is a static page, and browsers block most cross-site requests anyway. You choose the links yourself, and the tool only checks that each URL is a full http(s) address.
Inputs, outputs and limits
Inputs
- Site name
- Summary and extra notes
- Sections with link title, URL and description
- Optional links
Outputs
- llms.txt Markdown text
- Validation messages for missing names, titles and invalid URLs
- Copy and download as llms.txt
Limits
- Does not crawl or fetch any page; links are what you type.
- Only checks that URLs are valid http(s) addresses, not that they load.
- Descriptions are collapsed to a single line.
- Does not generate the longer llms-full.txt variant.
Processing
- The file is built in your browser. Nothing you type is uploaded, stored or sent to analytics.
Frequently asked questions
Do I need an llms.txt file?
No. It is optional and unofficial. Some teams publish one to make documentation easier for AI tools to find; there is no guarantee it is read or that it affects AI visibility.
Does llms.txt block AI crawlers?
No. It only lists pages. To allow or block crawlers use robots.txt, and keep in mind that is advisory too. The AI crawler robots.txt builder covers that.
Where do I put the file?
At the root of your domain so it is reachable at /llms.txt, served as plain text or Markdown.
Why does the tool not scan my site?
This is a static, browser-only tool. It cannot crawl other sites reliably, and keeping it form-based means you control exactly which pages are listed.
What should the Optional section contain?
Pages that are useful but not essential, such as a changelog, older docs or long reference pages. The proposal says these can be skipped when a shorter context is needed.
Need an assistant connected to your own knowledge?
We build AI assistants and automations grounded in your documents and systems, with access controls and evaluation built in.