llms.txt generator.
Write the file that tells AI models what your site is and which pages matter. It builds as you type, runs in your browser, and nothing is sent anywhere.
Becomes the > line. Models read it as your primary summary.
Sections
Group your key pages into categories.
Generated in your browser. Nothing is sent to any server.
What is llms.txt?
llms.txt is a proposed standard for helping large language models understand your website. It sits at yourdomain.com/llms.txt and is a plain Markdown file that describes your site: what you do, what is on it, and which pages matter most.
It was proposed by Jeremy Howard of Answer.AI. robots.txt tells crawlers what not to read. llms.txt tells AI models what to read and how to understand it.
The format is minimal: a heading with your site name, a one-line description, an optional paragraph, and sections listing key pages with links and short descriptions.
Ten minutes of work. No downside.
01
Context for AI crawlers
AI search tools crawl the web constantly. An llms.txt gives them a structured, authoritative summary of your site in a form they can use.
02
Better citations
When a model knows what each page covers, it cites the right page for the right question instead of guessing or skipping you.
03
Zero risk
It is a static text file. No performance cost, no SEO risk, and almost no maintenance.
How to use it.
- 01
Generate it above
Fill in your site details, add your key sections and pages, then download the file.
- 02
Host it at your root
Upload it so it lives at yourdomain.com/llms.txt. On most platforms that is the /public or /static folder.
- 03
Consider llms-full.txt
For content-heavy sites, add a companion file with the full text of your most important pages.
- 04
Keep it current
Update it when you add major sections or change positioning. A quarterly check works for most sites.
Questions, answered.
01 Is llms.txt an official standard?
Not yet. It was proposed by Jeremy Howard of Answer.AI in 2024 and has gained wide adoption among developers and companies. It's a de facto standard, not a specification from any official body. AI crawlers are already reading them.
02 What's the difference between llms.txt and robots.txt?
robots.txt tells crawlers what not to index: it's a blocklist. llms.txt is a guide for what to read and how to understand your site. They serve opposite purposes and you should have both.
03 Does ChatGPT actually read llms.txt?
OpenAI's crawlers (OAI-SearchBot and GPTBot) can read the file. AI search tools like Perplexity actively use it. Adoption is growing fast across the major AI platforms.
04 Do I need a developer to deploy it?
No. It's a plain text file. If you can add a file to your website's root directory, you can deploy llms.txt. On most platforms like Webflow, WordPress, and Squarespace you can upload it directly without any code changes.
05 What's the difference between llms.txt and llms-full.txt?
llms.txt is a concise index: titles, links, short descriptions. llms-full.txt is an extended version with the actual full content of your pages. Start with llms.txt, then add llms-full.txt for content-heavy pages you want LLMs to read in depth.
06 How often should I update it?
When you add major new pages, change your core positioning, or retire old content. Quarterly works for most sites. Treat it like a profile in a business directory: keep it current but it doesn't need constant attention.
07 Will llms.txt affect my Google SEO?
No. Googlebot ignores llms.txt entirely. It has no effect on PageRank or crawl behavior. Only AI-specific crawlers read it.
08 What pages should I include?
Your most important pages: product or service pages, pricing, documentation, case studies, about, and key blog posts. Focus on pages you want an LLM to reference when someone asks about your topic or category.
09 Can I have multiple llms.txt files?
The standard specifies one file at the root of your domain. If you run multiple products or subdomains, each can have its own llms.txt. For example, docs.yoursite.com/llms.txt for a documentation subdomain.
10 Is there a size limit?
No official limit exists, but keep it concise. The goal is to give LLMs a useful summary, not a dump of your entire site. If you need to include full content, use llms-full.txt as a companion file.
A file is a start. Being cited is the goal.
llms.txt helps models read you. A GEO program is what gets you recommended across ChatGPT, Perplexity and Google AI Overviews.
See the GEO practice