How the llms.txt generator works
- We fetch yoursite.com/llms.txt. If it is there, we check it against the format, line by line, and mark the lines with problems.
- No file? We read your sitemap (or your homepage links), take up to 30 pages and their titles, and group them into sections.
- You edit the draft in the page, then copy or download it and upload it as /llms.txt at the root of your site.
Honest note: few AI crawlers read llms.txt yet
In a June 2026 study of 137,210 domains, Ahrefs found that 97% of llms.txt files received no requests in a month, and that most of the requests that did arrive came from SEO audit tools and other bots, not AI assistants. So an llms.txt won’t get you cited by ChatGPT on its own. It is cheap insurance: a few minutes of work, in case more AI tools start reading it. What decides whether assistants use your pages today is whether their crawlers can read them (test that with the AI crawler checker) and whether your pages answer the question better than the ones cited now.
The llms.txt format
The format is defined at llmstxt.org. The only required part is the H1. A useful file has a summary and a few sections of links:
# Acme > Acme is invoicing software for freelancers in the EU. ## Docs - [Getting started](https://acme.com/docs/start): set up in five minutes - [Pricing](https://acme.com/pricing): plans and limits ## Optional - [Changelog](https://acme.com/changelog)
An H2 named “Optional” marks links a tool can skip when it needs a shorter context.
What the validator checks
| Rule | What we look for | If it fails |
|---|---|---|
| H1 first | The file starts with # Site name, and has exactly one H1 | Error |
| Summary | A > blockquote right after the H1 | Suggestion |
| Link sections | ## sections whose items are - [name](url): notes | Error if a list item has no link |
| Full URLs | Links start with https://, not /relative paths | Suggestion |
| No duplicates | Each URL listed once | Suggestion |
| Served as text | Not an HTML page (a 404 or homepage served at /llms.txt) | Error |
| Size | Under about 100 KB; full text belongs in llms-full.txt | Suggestion |
FAQ
What is llms.txt?
A Markdown file at the root of a site (yoursite.com/llms.txt) that lists its most useful pages for AI tools: an H1 with the site name, a one-line summary, then sections of links with short notes. It was proposed at llmstxt.org in 2024. It is a convention, not a standard that search engines or AI assistants have committed to.
Does llms.txt help me show up in ChatGPT or Google AI Overviews?
There is no evidence that it does today. In Ahrefs' study of 137,210 domains, 97% of llms.txt files got no requests in a month. Treat it as cheap insurance: being readable by AI crawlers and answering buyer questions well matter far more.
What is the difference between llms.txt and llms-full.txt?
llms.txt is a short index of links. llms-full.txt is an optional companion that puts the full text of your key pages in one Markdown file, so a tool can read everything in one request. This generator builds llms.txt; keep llms-full.txt for documentation-style sites where the full text is useful.
Where do I put the file?
At the root of your domain, served as plain text: https://yoursite.com/llms.txt. On WordPress, an SEO plugin or a file upload to the site root works; on Shopify, Webflow and similar platforms, check whether they let you serve a root file or use their llms.txt setting if they have one.
Is anything stored?
No. We fetch /llms.txt and, if there is none, your sitemap and up to 30 page titles. The result is shown once and not saved. Pasted files are checked in your browser and never sent to us.
Learn more
- The page structure AI assistants actually cite
- Every AI crawler, its robots.txt token and what it does
More free tools
- SaaS website auditCheck the pricing, comparison and alternatives pages AI quotes for software.
- AI prompt research toolFind the questions buyers ask about your category, by intent.
- Brand entity checkerDo Wikidata, Wikipedia and your schema know who you are?
- Website SEO checkerAudit 25 pages for SEO and AI readiness, with a 0-100 score.
- Broken link checkerFind dead internal and external links on 25 pages.
- Redirect checkerFollow every hop of a URL as a browser, Googlebot and AI crawlers.
- Indexability checkerCan Google, Bing, ChatGPT, Perplexity and Claude index this page?
- XML sitemap checkerValidate your sitemap and test the pages it lists.
- Title tag checkerCheck title and meta description length with a Google preview.
- AI crawler checkerCan GPTBot, ClaudeBot and PerplexityBot read your site?
- AI readiness page checkScore one page on the structure AI assistants quote.
- AI content graderGrade your writing on what AI assistants quote, problems highlighted.
- AI crawler log analyzerSee how often GPTBot, ClaudeBot and PerplexityBot crawl you. Runs in your browser.
- GA4 AI traffic regexTrack visits from ChatGPT, Perplexity and other assistants.
- robots.txt generatorBuild a robots.txt with rules for every AI crawler.
- Schema markup generator and checkerBuild JSON-LD with a live preview, or check a page's schema.
- Open Graph checkerSee your link preview on X, LinkedIn, Facebook, Slack and iMessage.
- SPF, DKIM and DMARC checkerGrade your domain's email authentication from A to F.
- Site optimizer (GEOHATS)Runs these checks on every page of your site and suggests the fixes.
By Daniel Borodin, GEOHATS founder · Last updated