llms.txt Generator & Validator
Describe your site and its key pages to get an llms.txt file, or validate the one you have.
Runs in your browser. Nothing is uploaded.
Becomes the blockquote under the title. Keep it short and factual.
Plain paragraphs or lists. Do not use headings here.
Set it to type links as paths like /pricing; they become full URLs in the file.
The structure matches the llmstxt.org format.
Some links are paths, not full URLs. Fill in the site URL to turn them into absolute links.
Where it goes
Upload the file to the root of your site so it opens at https://your-site.com/llms.txt, served as plain text. Next, check which AI crawlers your robots.txt lets in with the AI robots.txt generator.
Open your-site.com/llms.txt in a browser and copy everything. The check runs here; nothing is fetched or sent.
Paste a file to see its structure and any problems, with line numbers.
No problems found. The file follows the llmstxt.org structure.
Fix the errors first: tools that parse llms.txt may not read the file correctly.
Outline
- ·
How to make an llms.txt file
- Enter the name of your site or product. It becomes the H1 title, the only part of the file the format requires.
- Write a summary of one or two sentences: what the site is, who it is for, and what makes it different. It becomes the blockquote under the title.
- Add sections such as Docs, Product or Pricing, and list the pages that matter in each one: a title, a URL and a short note on what the page covers.
- Put secondary pages, such as the blog or the changelog, under Optional.
- Download the file and upload it to the root of your site, so it opens at
/llms.txt.
If you fill in the site URL, you can type links as paths like /pricing and the tool turns them into full URLs. Your draft stays in this browser, so you can come back to it later.
What the format looks like
The format comes from the proposal at llmstxt.org. A complete file is short:
# Example Notes
> Example Notes is a note-taking app for small teams, with shared notebooks, offline sync and a REST API.
Plans: Free (3 notebooks), Team ($8 per user per month) and Business.
## Docs
- [Getting started](https://example.com/docs/start): Create an account and your first notebook
- [API reference](https://example.com/docs/api): Endpoints, authentication and rate limits
## Optional
- [Changelog](https://example.com/changelog)The order is fixed: the H1 name, a blockquote summary, then any paragraphs or lists without headings, then sections that start with ## and contain lists of links. Each item is a Markdown link, optionally followed by a colon and a note. A section called Optional marks links that a tool can skip when it needs a shorter context.
What the validator checks
Paste an existing file into Validate a file to check its structure. Every message has a line number.
- Errors break the structure: no H1 or more than one, an H1 that is not the first line, broken link syntax, links with no text or no URL.
- Warnings are things a parser may misread: a missing summary, headings between the summary and the first section, relative URLs such as
/docs, list items without a link, notes not separated by a colon, duplicate links and empty sections. - Notes are style points, such as plain text inside a link section or an Optional section that is not last.
The validator checks the format only. It does not open your links, so it cannot tell you whether a page exists.
Tips for a useful file
- Link the pages that answer real questions: documentation, pricing, plan limits, policies, the FAQ. Leave out sign-in pages and pages that say little.
- Keep the notes factual. One short line per link is enough.
- The proposal also suggests offering clean Markdown versions of pages at the same URL with
.mdadded. That is optional; llms.txt works without it. - Update the file when pages move. A list of broken links is worse than none.
Deciding which AI crawlers may visit at all is a separate job for robots.txt. The AI crawler robots.txt generator writes those rules, and our SEO tools category lists services that track how AI search engines cite you.
Where do I put llms.txt?
At the root of your site, so it opens at https://your-site.com/llms.txt, served as plain text in UTF-8. The proposal also allows a file inside a subfolder for that part of the site, but the root is where tools look first.
Does llms.txt replace robots.txt or sitemap.xml?
No. robots.txt tells crawlers what they may fetch, and a sitemap lists URLs for search engines. llms.txt is a short, curated reading list for language models. A page blocked in robots.txt stays blocked even if llms.txt links to it.
Will llms.txt improve my rankings in Google or ChatGPT?
There is no evidence that it does. It helps a model find the right pages when it reads your site; the pages themselves still have to rank on their own.
What is llms-full.txt?
A convention some documentation platforms use: a single file with the full text of every page. It is not part of the llmstxt.org proposal. This tool makes llms.txt only.
Should links be absolute or relative?
Absolute, starting with https://. The file is often read outside your site, where a path like /docs cannot be resolved. The validator warns about relative links for that reason.
Does the tool crawl my site?
No. You type the pages yourself, and nothing you enter is uploaded. That also means it cannot check whether your links work.
SEO tools from our directory
Transforms complex search data into actionable insights for improvement.
Create professional landing pages and sales funnels effortlessly.
