Free llms.txt Generator and Validator
Create an llms.txt file in the correct format, or check an existing one for errors. Plus an honest look at which AI tools actually read it.
How to use the llms.txt generator
- Enter your site or project name. It becomes the H1, the only line the format requires.
- Add a one or two sentence summary. It becomes the blockquote that tells a model what the site is.
- Add sections of links, one per line as
Name | URL | note. Typical sections are Docs, Guides, Products or Policies. - Tick Add an Optional section if you want a place for secondary links that a tool can skip when space is tight.
- Download
llms.txtand upload it to the root of your site, so it loads atyoursite.com/llms.txt.
Switch to Check a site to fetch a live llms.txt and test it against the format rules.
What llms.txt is
llms.txt is a proposed standard from llmstxt.org: a plain Markdown file at the root of a site that gives AI tools a short, curated map of the content that matters. It is meant to be read at the moment a tool needs it, rather than crawled like a sitemap.
The format is simple:
| Part | Required | What it holds |
|---|---|---|
# Title |
Yes | The name of the site or project |
> Summary |
No | A short blockquote explaining what it is |
| Free text | No | Paragraphs or lists with extra context. No headings |
## Section |
No | Lists of links written as - [Name](url): note |
## Optional |
No | By convention, links a tool can skip when it needs a shorter context |
llms-full.txt, a single file containing the full text of a site, is a common convention but is not part of the llms.txt spec.
Does anything actually read llms.txt?
This is the honest part. Google says Search, including its AI features, ignores llms.txt and that adding one will neither help nor harm rankings. No major AI search engine, including ChatGPT, Claude, Perplexity or Gemini, has said its crawler reads other sites' llms.txt files. Log studies show crawlers request it rarely compared with robots.txt.
Where it does help is with tools that go looking for it: AI coding assistants reading developer documentation, some agent frameworks, and Chrome's Lighthouse, which added an llms.txt audit for agentic browsing in 2026. The big AI labs publish llms.txt files for their own documentation for exactly this reason.
So treat it as cheap and harmless rather than a ranking lever. If you run documentation, an API or a product that people use with AI tools, it is worth ten minutes. If you want to be cited in AI answers, links, mentions and well-structured pages still do the heavy lifting, which the guides on LLM SEO and brand mentions cover.
What the checker looks for
- The file starts with a single H1
- Only H1 and H2 headings are used
- Every line in an H2 section is a Markdown list link,
- [Name](url)with an optional: note - Links are full URLs, so a tool reading the file out of context can follow them
- A blockquote summary is present (recommended, not required)
- The URL returns a real text file, not an HTML page or a soft 404
Frequently asked questions
Is llms.txt the same as robots.txt? No. robots.txt tells crawlers what they may access. llms.txt is a reading list that points AI tools at your best content. It cannot block anything. To control AI crawlers, use the robots.txt generator.
Will llms.txt get me into ChatGPT or AI Overviews? There is no evidence it does. Google has said its AI features don't use it, and no other major AI search provider has confirmed reading it.
Where does the file go?
At the root of the domain, for example https://example.com/llms.txt. It can also sit in a subfolder for a docs site, such as /docs/llms.txt.
How long should it be? Short. The point is curation, so list the pages a newcomer would need first, not every URL on the site. Your sitemap already does that job.