Free tool, no sign-up
llms.txt generator
Enter a domain. We read your home page and main pages and draft a spec-compliant llms.txt.
How to use it
- Generate. We read your home page and up to 10 pages linked from its navigation. An AI model then writes the name, a short summary and a one-line description for each page.
- Review. The draft is editable. Remove pages you do not want agents to start from and fix any description that is off.
- Publish. Save it as llms.txt and serve it from the root of your domain, for example https://example.com/llms.txt. Then confirm it with the AI crawler check.
What goes in the file
An H1 with the site name is the only required part. After it come a blockquote summary and H2 sections that hold lists of links, each written as [name](url) with optional notes after a colon. A section called Optional holds links an agent can skip when it needs a shorter context. Read the full story in the llms.txt guide.
# Example Co
> Example Co sends invoices for freelancers and tracks payment.
## Product
- [Pricing](https://example.com/pricing): Plans and what each includes
- [Docs](https://example.com/docs): How to connect a bank account
## Optional
- [Privacy policy](https://example.com/privacy): How customer data is handledQuestions about llms.txt
What is llms.txt?
A proposed standard: a markdown file at /llms.txt that gives AI agents a short, curated guide to a site. Jeremy Howard of Answer.AI proposed it and the format is described at llmstxt.org.
Do AI engines use it to decide what to cite?
We have not found an engine that documents llms.txt as an input for choosing citations. Documentation platforms publish it and coding agents read it. Google says nothing beyond being indexed and eligible for a snippet is needed to appear in AI Overviews or AI Mode. Treat llms.txt as cheap preparation, not a ranking lever.
Which model writes the draft?
A small AI model: Google Gemini Flash-Lite, with Anthropic Claude Haiku as backup. It receives page titles, descriptions and link text from your site, and every link in the final file is a page we actually fetched.
Do you store my site or the file?
No. We keep only a daily counter keyed by a hash of your IP address. The limit is 10 files a day.
Why is my file short?
We follow up to 10 links from the navigation. Sites that build their navigation with JavaScript, or block our requests, give us less to read. You can add links by hand.
A file guides agents. A scan shows what engines say.
Run a free scan to see whether Perplexity and Claude mention your brand today.
Scan my brand