Free tool
Free llms.txt generator
An llms.txt generator builds the plain-text file AI models read at yoursite.com/llms.txt: your site name, a one-line summary, and your most cite-worthy URLs, in the markdown format the llms.txt standard defines. Fill the form, watch the file build live, copy or download. No signup, and nothing you type leaves your browser.
1 · Describe your site
2 · Key pages
Your most cite-worthy URLs: about, collections, guides, policies.
3 · Products (optional)
Hero products or category hubs you want agents to reach first.
4 · Secondary links (optional)
Lower-priority URLs. Agents may skip this section when context is tight.
Live preview · llms.txt
# Your Site Name > One or two sentences on what the site is and who it serves.
Upload the file to your site root so it resolves at yoursite.com/llms.txt. Everything runs in your browser - nothing is sent to us.
Why bother with llms.txt?
When a shopper asks ChatGPT, Claude, or Perplexity what to buy, the model works from whatever picture of your site it can assemble. llms.txt - proposed by Jeremy Howard of Answer.AI in September 2024 - is the emerging convention for handing models that picture directly: a curated index at your site root instead of whatever a crawler pieced together.
It costs nothing to host and takes minutes to write with this tool. Adoption across AI providers is still uneven, so treat it as one layer of AI search readiness - our complete llms.txt guide for ecommerce brands covers what to include, real examples, and where it fits next to schema markup. The glossary entry has the short version, and our own file at trucommerce.ai/llms.txt is a working example.
Three placement rules: the file lives at the root (not a subdirectory), it stays plain markdown (no HTML), and every link resolves. Then check the rest of your agent readiness - the free agentic readiness scan runs 147 checks in about ten seconds, llms.txt included.
The file tells models about you. Are they listening?
llms.txt is the input. Citation Rank measures the output: where your brand actually surfaces across ChatGPT, Gemini, Perplexity, Rufus, Copilot, and Claude.
Rather poke at it yourself first? The scan is self-serve and free.
Run the scan yourself →no card · free
llms.txt generator FAQ
llms.txt is a plain-text markdown file at your site root (yoursite.com/llms.txt) that gives AI models a curated introduction to your site: an H1 name, a blockquote summary, and H2 sections of links to your most important pages. It was proposed by Jeremy Howard of Answer.AI in September 2024.
No. robots.txt tells crawlers what they may not access; llms.txt tells AI models what your site is and which pages matter most. They complement each other - keep both, and don't put crawl directives inside llms.txt.
Place it at your domain root so it resolves at yoursite.com/llms.txt. On Shopify, upload via Settings → Files and add a redirect, or use an app that serves root files. On WordPress or static hosts, drop it in the public root directory.
No. The whole tool runs client-side in your browser. Nothing you type is stored, sent to our servers, or gated behind an email. Copy or download the file and you're done.
Lead with a factual one-line summary of what you sell and who you serve, then link your about page, top collections or category hubs, shipping and returns policies, and any buying guides. Put hero products in a Products section and lower-priority links under Optional.
Adoption is uneven and no provider guarantees it. The standard is being picked up as a discovery hint, and hosting one costs nothing - for models that honor it, it steers how your brand is summarized. Treat it as a low-effort layer on top of schema markup and crawlable content, not a replacement.
A companion convention: while llms.txt is a curated index, llms-full.txt inlines the full content of your key pages into one file so a model can ingest everything in a single fetch. Start with llms.txt; add llms-full.txt if you have deep documentation or content-heavy pages.
Whenever your key pages change - new collections, renamed products, updated policies. For most stores a quarterly review is enough. A stale llms.txt that links to dead URLs is worse than none.