Assistant fetchers
kagi-fetcher is a bot that fetches single pages on demand for an AI assistant, and its operator has not been publicly identified. kagi-fetcher is an AI Assistant operated by Kagi that fetches web content to answer user queries through Kagi AI, their suite of AI-powered tools including Assistant, Res…. No IP range list or reverse-DNS convention is published, so a request carrying this user agent cannot be proven genuine and a robots.txt rule alone will not stop a forgery.
Request says
"kagi-fetcher"
Checked against
Nothing published
Live check
No operator check exists for kagi-fetcher. This still shows what the address really is.
Reference
| User agent | kagi-fetcherToken only: match on the substring. |
|---|---|
| Operator | Not publicly identified |
| Purpose | Assistant fetchers |
| Respects robots.txt | No policy |
| Verification method | Claim onlyNone published, user agent only No IP range file and no reverse-DNS convention have been published for this agent. The user-agent string is the only signal, and any client can send it, so treat a match as a claim rather than proof. |
| Crawl pattern | Not published |
| Robots.txt tokens | kagi-fetcher |
| Operator documentation | None published |
kagi-fetcher is an AI Assistant operated by Kagi that fetches web content to answer user queries through Kagi AI, their suite of AI-powered tools including Assistant, Res…
robots.txt
Paste one at the root of your domain. Rules are per token.
User-agent: kagi-fetcher
Disallow: /User-agent: kagi-fetcher
Allow: /User-agent: kagi-fetcher
Allow: /
Disallow: /account/
Disallow: /checkout/
Disallow: /searchEdit the Disallow paths to match your own URLs.
Blocking kagi-fetcher means a person who asks about one of your URLs gets an error instead of a summary. That is a support and reputation trade-off, not a training one.
Build a file for every crawlerFAQ
kagi-fetcher is a bot that fetches single pages on demand for an AI assistant, and its operator has not been publicly identified. kagi-fetcher is an AI Assistant operated by Kagi that fetches web content to answer user queries through Kagi AI, their suite of AI-powered tools including Assistant, Res…. No IP range list or reverse-DNS convention is published, so a request carrying this user agent cannot be proven genuine and a robots.txt rule alone will not stop a forgery.
Not documented. No operator statement says whether kagi-fetcher reads robots.txt, so add the rule but verify in your logs that the requests actually stop.
You cannot, at least not from the request itself. No IP range file and no reverse-DNS convention have been published for this agent. The user-agent string is the only signal, and any client can send it, so treat a match as a claim rather than proof. Compare the source IP against hosting and datacenter ranges instead, and rate limit anything that behaves like a crawler.
Add the kagi-fetcher token to robots.txt with Disallow: /. If the crawler ignores robots.txt, match the user agent at your CDN or reverse proxy and return 403 there instead.
Blocking kagi-fetcher means a person who asks about one of your URLs gets an error instead of a summary. That is a support and reputation trade-off, not a training one.