Free tool
llms.txt validator and generator
Check your /llms.txt against the llmstxt.org format line by line and see whether its links answer, or draft a first version from your homepage, navigation and sitemap.
Example result
- # Example
- > One line on what the product does.
- ## Docs
- - [Quick start](https://example.com/start): Install and first run
- - [API](https://example.com/api) - every endpoint
- CheckLine 7: notes after a link need a colon
Your check shows up here
We read /llms.txt on your site, check it line by line against the format, and request its first 10 links.
How it works
Three steps, about ten seconds
Enter your site
Your domain, or the full address of an llms.txt that lives below the root, like /docs/llms.txt.
We read the file
Each line is checked against the format and against how the two reference parsers read it, then the first links are requested.
Or we write one
Choose Write a draft and we build a file from your own page titles and descriptions, for you to edit.
Reference
The llms.txt format, part by part
From the llmstxt.org specification, in the order a file has to hold them. The file lives at /llms.txt, or at a path below the root to cover only that part of a site.
| Part | Required | How it looks | Rule |
|---|---|---|---|
| Title | Yes | # Your product | The first line of the file, and the one part the format requires. |
| Summary | No | > One line on what it is | A blockquote straight under the title. |
| Details | No | Paragraphs or lists | Anything except headings, before the first section. |
| Section | No | ## Docs | Each one holds a list of links and nothing else. |
| Link | No | - [Name](https://url): notes | A dash, the link, then a colon before any notes. |
| Optional | No | ## Optional | Links an agent can skip when it is short of room. |
Fix it on your platform
Publish llms.txt on your platform
The file has to answer at /llms.txt as plain text. A page that only looks like it, or a 404, is what most checks find.
Next.js
Put the file at public/llms.txt and it is served at /llms.txt. To build it from your content instead, add a route handler at app/llms.txt/route.ts:
export function GET() {
return new Response("# Your product\n\n> One line on what it is.\n", {
headers: { "content-type": "text/plain; charset=utf-8" },
});
}WordPress
Yoast SEO and AIOSEO can each generate an llms.txt for you; llmstxt.org lists both. Or upload your own file to the site's root folder.
Framer
On Pro and Enterprise plans, open Site Settings, then Hosting, then Files, and upload llms.txt. It answers at /llms.txt once you publish.
Wix
Wix generates an llms.txt for a site on a paid plan with a connected custom domain and search engine indexing turned on. Find it in SEO & GEO, under Tools and settings, and check what it holds with the validator above.
Docs platforms
Mintlify and GitBook serve an llms.txt for the docs sites they host. If your docs live on a subdomain or under /docs, enter that address to check its file.
Questions, answered
llms.txt, in plain terms
01What is llms.txt?
- A markdown file at /llms.txt that tells AI agents what your site is and where its most useful pages are.
- The format comes from llmstxt.org: a title, a short summary, then sections of links with a note on each.
02Do ChatGPT, Claude or Google read llms.txt?
- Coding agents and assistants read it when they are pointed at it, and OpenAI, Anthropic and Google publish their own for their developer docs.
- No search or answer engine has said it ranks or cites a page because of llms.txt. Treat it as a map for agents, not a ranking signal.
- Chrome's Lighthouse looks for one in its agentic browsing checks.
03Is llms.txt the same as robots.txt or a sitemap?
- No. robots.txt says what a crawler may fetch. llms.txt is a reading list, and it blocks nothing.
- A sitemap lists every page for search engines. llms.txt picks the few that explain your product.
04Why does my llms.txt show my homepage?
- Many single-page apps answer every unknown path with the app itself, so /llms.txt looks found but holds a web page.
- Serve a real text file at the root, or a route that returns it as text/plain.
05What do the warnings about the reference parsers mean?
- llmstxt.org publishes two parsers. The Python one reads every line under a ## heading as a link and fails on any other line. The JavaScript one skips those lines.
- Keep prose above the first ## heading and only links below it, each line starting with - and a link.
06Should I publish llms-full.txt too?
- Some sites put one beside llms.txt: a single file with the full text of their pages. It is a convention, not part of the format.
07Is it free, and do you keep my file?
- It is free and needs no account. Drafts are capped at 10 a day per connection, because each one reads up to 20 pages.
- A result stays in memory for a few minutes so a repeat check does not hit your site again, then it is gone. Nothing is saved to a database or published.
More free tools
- AI crawler checkerWhich AI crawlers your robots.txt lets in, and what each one gets when it asks for your page.
- ChatGPT search checkerWhether OAI-SearchBot and Bingbot can reach your page, and whether the page lets them show it.
- Indexability checkerStatus, redirects, canonical, robots meta, X-Robots-Tag and robots.txt for one URL, as Googlebot reads it.
- Meta tag checkerYour title and meta description as a results page prints them, with the lengths that get cut.
- Open Graph previewYour og: and twitter: tags, the image they point at, and how the link card looks in five apps.