Free tool · No signup
llms.txt generator
Build a clean markdown llms.txt — the emerging AI-readable site index that ChatGPT, Claude, Perplexity and similar use to understand what your site is and where to find canonical content.
Inputs
Key pages
Optional pages
Your llms.txt
# Your Brand
> Official website of Your Brand. Replace this line with a 1-2 sentence summary.
## Key pages
- [Homepage](https://yoursite.com/)
- [About](https://yoursite.com/about): Who we are and what we do.
- [Services](https://yoursite.com/services): Our services and offerings.
- [Pricing](https://yoursite.com/pricing): Plans and pricing details.
- [Contact](https://yoursite.com/contact): Get in touch.
## Optional
- [Blog](https://yoursite.com/blog): Latest articles and insights.
Drop this at the root of your site as /llms.txt.
Why bother with llms.txt?
Most sites hand AI crawlers a tangle: HTML wrapped in JS, navigation menus, ads, footers, sidebars. The model has to infer what’s important. That guesswork is where citations get lost.
llms.txt cuts the guesswork. You curate a markdown index of the pages that matter and what they’re about. AI engines fetch it first, get an editorial overview, then dive into the right pages with context.
Adoption is small but growing. Anthropic, Cloudflare, and a long tail of dev-tool / SaaS / docs sites have shipped llms.txt files. Early movers report disproportionate citation lift on Perplexity and ChatGPT’s browse-mode.
llms.txt format — the rules
- First line:
# Your brand name(a single H1). - Optional blockquote next:
> A 1-2 sentence summary. ## Sectionheadings group pages. Key pages is conventional for the must-read list.- Each page is a list item:
- [Label](URL): description. ## Optionalat the end for less-critical pages — by convention LLMs may skip these when context is tight.
FAQ
What is llms.txt?+
llms.txt is a markdown file at your site root (yoursite.com/llms.txt) that tells AI engines what your site is about and where the most important content lives. It's an emerging standard proposed at llmstxt.org and gaining adoption with sites that want to be cited cleanly by ChatGPT, Claude, Perplexity and similar.
How is llms.txt different from sitemap.xml or robots.txt?+
Sitemap.xml lists every URL on your site (for crawlers). Robots.txt controls who can access what. llms.txt is for HUMANS — and LLMs that summarise your site. It's curated, prose-driven, and points to your most important pages with brief descriptions. Think of it as an AI-readable About page.
Where does llms.txt go?+
Always at the root of your domain: https://yoursite.com/llms.txt. AI engines look for it there by convention. Some sites also publish a richer /llms-full.txt with the actual content of key pages inlined — useful for documentation sites.
Does llms.txt actually improve my AI rankings?+
It's an early signal — adoption is small but growing fast. Sites with a clean llms.txt tend to get cited more often by Perplexity Sonar (which uses live web data) and by AI surfaces that fetch context at query time. The best evidence is anecdotal but consistent: early movers report measurable lift in citation rates.
Do I need llms.txt if I already have good schema?+
They solve different problems. Schema (JSON-LD) gives AI engines structured FACTS about specific pages. llms.txt gives them an EDITORIAL OVERVIEW of the whole site. Both help. The full Aapta GEO scan checks for both — and 38 other AI-readiness signals.
Want a full AI-Readiness audit?
This tool fixes one signal. The full scan checks 40+ across 6 categories — bot access, structured data, content answerability, authority, technical foundations, and emerging AI standards.
Run the free AI-Readiness scan →