These are free, public tools for finding out how AI crawlers and assistants read your website. Each one works from signals anyone can read from the outside, so nothing is installed on the site being checked and no account is needed.
Built for the person who runs the site, not for an analyst.
AI assistants answer from pages they were able to fetch. Two things decide whether yours are among them: whether a crawler can reach your pages at all, and whether what it reads makes sense out of context. The checker below answers the first. The llms.txt tool answers the second, by building the small file that states in plain language what your site is for and which pages matter most.
Can AI systems reach and read my site at all?
Fetches your homepage as each major AI crawler and reports what came back: the live status codes, what your robots.txt allows, whether your pages read without JavaScript, and the structured data you are missing.
Run a checkDoes my site tell a model what it is for, and is that file correct?
Builds an llms.txt file from the pages your site already publishes, using your own titles and meta descriptions and no AI writing. Checks a file you already have against the llmstxt.org specification and reports every finding with its line number.
Generate or checkBoth tools read your site from the outside at one moment. That is enough to find a crawler a firewall is turning away, or a file that breaks its own format. It is not enough to tell you which crawlers actually arrived last week, how often they came back, or whether any of that attention sent you a paying visitor. Only your own server sees that, which is what Kymo records.
Beyond the tools, the AI crawler directory documents every user agent and robots.txt token one operator at a time, the answer engine optimization guide covers the wider practice, and the documentation explains how Kymo records crawler traffic on a site you own.