llms.txt & AI Crawler Generator
Generate llms.txt and llms-full.txt for ChatGPT Search and Perplexity indexing.
Guide to llms.txt and AI Crawlers
ChatGPT Search, Perplexity and similar answer engines summarize sites through /llms.txt and /llms-full.txt. This tool generates both files from your site name, page list and contact details. Below I explain what the standard is for, how it differs from robots.txt and how to use it together with an AEO audit.
What does llms.txt solve?
HTML pages are noisy: navigation, cookie banners, related posts. llms.txt gives agents the title, summary and link list you choose. llms-full.txt is for longer context; it collects policy, product and contact paragraphs in a single file. When you place it at the root or a well-known path, crawlers no longer have to guess your site map.
How it relates to robots.txt and ai.txt
robots.txt controls crawl permission; llms.txt describes how the allowed content should be read. To block or separate bots, use robots.txt & AI Bot Control. Once crawling is allowed, publish the summary file with this generator.
AEO audit and schema
After publishing the file, measure how quotable your pages are with AEO & LLM SEO Auditor. For FAQ and HowTo markup, use the JSON-LD Schema generator. Together, the three tools improve your chances of being cited as a source by answer engines.
Publishing tips
Use absolute URLs, leave no broken links and keep the summary to two sentences. In the Next.js App Router, returning plain text from app/llms.txt/route.ts is common. Keep the file up to date; pages for discontinued products send agents in the wrong direction.
I explain what the standard is for in the post llms.txt nedir, nasıl çalışır (in Turkish).