Kagi Assistant
Operated by Kagi
Quick Facts
- User-Agent:
- kagi-fetcher
- Category:
- AI & LLM Bots
- Operator:
- Kagi
- Safety:
- Safe
- Blocking Impact:
- Low - No SEO ranking impact
- SEO Impact Score:
- 2/10
- Official docs:
- None published by Kagi
Reported, not operator documented
Kagi has not published a crawler page that names kagi-fetcher. It is listed here on our own evidence. Verified by AI Crawler Check: 26 of the 5,583 valid robots.txt files in the Tranco top 10,000 carry a rule for kagi-fetcher, so site owners treat it as a real crawler name (how we measure this). That proves the spelling is in use, not who sends it. Reported Kagi on-demand fetcher; Kagi documents only Kagibot.
What that means for you: the kagi-fetcher rule on this page is the best available spelling, but Kagi has made no statement of purpose, crawl rate or robots.txt compliance. Treat a kagi-fetcher request in your logs as a clue, not proof of who sent it, and add a firewall rule if that traffic matters to you. If the operator publishes documentation, this profile moves to Official docs.
What is Kagi Assistant?
Kagi Assistant is an on-demand AI fetcher operated by Kagi. It retrieves a page only when a user explicitly asks an AI assistant or agent to read, summarize, or act on a specific URL. Because it is triggered by real user intent rather than bulk crawling, blocking it mainly prevents users from pulling your content into Kagi's assistant.
Kagi Assistant is an on-demand AI fetcher operated by Kagi. It retrieves a page only when a user explicitly asks an AI assistant or agent to read, summarize, or act on a specific URL. Because it is triggered by real user intent rather than bulk crawling, blocking it mainly prevents users from pulling your content into Kagi's assistant.
Kagi Assistant uses the user-agent token kagi-fetcher. You can control it via robots.txt, meta tags (noai), or the emerging llms.txt standard. Robots.txt is voluntary; for hard enforcement, combine it with server-level IP blocking.
What happens if you block Kagi Assistant?
User-agent / Disallow: / without any SEO penalty.Want to see whether Kagi Assistant actually visits you? Read how do I monitor AI bot traffic to my website?
How to block Kagi Assistant with robots.txt
<code>User-agent: kagi-fetcher</code> - Matching is case-insensitive. Robots.txt is fetched from the root of each subdomain separately.
Is Kagi Assistant safe to allow?
What does Kagi Assistant do?
Understanding Kagi Assistant's purpose helps you decide whether to allow or block it.
- Fetches a page only when a user asks an AI assistant to read it
- Summarizes or extracts the URL the user provided
- Triggered by real user intent, not bulk crawling
- Low traffic volume compared with training crawlers
- Blocking it prevents users from pulling your content into the assistant
Kagi Assistant in context
Kagi Assistant is a user-triggered agent operated by Kagi. In plain terms, it fetches a page when a person asks an assistant or app to open it. Our database files it under AI and LLM crawlers and ranks it Tier 2, important crawlers from established AI and search operators. 74 of the 104 AI and LLM crawlers in our database share this tier.
Its safety rating is safe and its blocking impact is low. So the decision about Kagi Assistant rests on what you want from Kagi, not on its behaviour. How we rate safety and impact.
How site owners treat Kagi Assistant
In our own scan of the Tranco top 10,000 (5,583 valid robots.txt files), 26 files (0.5%) name kagi-fetcher in a User-agent line. That shows site owners treat the token as a real crawler worth a rule. It does not, on its own, prove who operates it.
Does it follow robots.txt?
Kagi Assistant's operator does not clearly document how it treats robots.txt. Write the Kagi Assistant rule anyway, then confirm in your logs that its requests stop.
Kagi crawlers and close alternatives
Kagi Assistant is one of 2 Kagi crawlers in our database. A User-agent: kagi-fetcher group controls Kagi Assistant only; the other Kagi tokens below need their own lines.
kagi-fetcher: this crawler (Tier 2)Kagibot: Kagi Search, builds a search or answer index (Tier 3)
To give Kagi Assistant the same answer as its siblings, stack User-agent: kagi-fetcher with their lines above one set of rules; to treat Kagi Assistant differently, give it its own group.
Other AI and LLM crawlers that do the same job (fetches a page when a person asks an assistant or app to open it) include ChatGPT Agent from OpenAI, ChatGPT Operator from OpenAI, ChatGPT-User from OpenAI, ChatGPT-User/2.0 from OpenAI, Claude-SearchBot from Anthropic, Claude-User from Anthropic. Deciding about Kagi Assistant is usually a decision about the whole group, so check how your file treats these too.
We first recorded kagi-fetcher on June 18, 2026. We could not find a page where Kagi names it, so treat the token as reported rather than documented.
Which rule Kagi Assistant actually follows
Kagi Assistant reads exactly one group in robots.txt, the most specific one that names kagi-fetcher, and never combines rules across groups. This short file shows the trap:
User-agent: *
Disallow: /private/
User-agent: kagi-fetcher
Disallow: /drafts/- Find the group. Kagi Assistant looks for a group naming
kagi-fetcher. One exists, so it ignoresUser-agent: *completely. - Apply only that group. It is refused
/drafts/and nothing else. - The surprise.
/private/is open to Kagi Assistant, because that rule lives in the*group it no longer reads. To keep it out of both, repeatDisallow: /private/inside its own group.
Test yourself: does a rule under User-agent: * apply to Kagi Assistant if the file also has a User-agent: kagi-fetcher group?
No. Once a group names it, Kagi Assistant reads only that group. Put every rule you want it to follow inside its own group.
Test yourself: will blocking Kagi Assistant remove your pages from AI answers?
Often, yes. Kagi Assistant is a user-triggered agent, so pages it cannot fetch can drop out of the answers or results it supports.
Test yourself: is User-agent: kagi-fetcher the same as User-agent: kagi-fetcher?
Yes. RFC 9309 makes user-agent matching case-insensitive. Paths are a different story: Disallow: /Blog/ does not block /blog/.
Should you allow Kagi Assistant? Decide by situation
| If you are... | Recommended setting |
|---|---|
| You publish content and want AI answers to cite it | Allow it. Kagi Assistant fetches pages for answers, so blocking it can remove you from them. |
| You license content and want to stop AI training | Blocking it does not stop training, because Kagi Assistant is a user-triggered agent. Block the operator's training crawler instead. |
| You run an online shop | Allow it on product and category pages, which are the pages shoppers ask assistants about. |
| Your server is under load from bots | Rate-limit before blocking. It is rated safe in our database. |
Check Kagi Assistant on your own site
- Open
/robots.txton your domain and search forkagi-fetcher. If it is not named, it followsUser-agent: *. - List the
Disallowlines in the group Kagi Assistant follows and test your key URLs against them; the longest match wins, andAllowwins a tie. - Look beyond the file. A firewall or bot manager can refuse Kagi Assistant even when robots.txt allows it, and that never shows in the file.
- Run our AI crawler access test to see how Kagi Assistant and every other crawler we track are treated in one pass, including firewall refusals.
Common mistakes with Kagi Assistant
The errors we see most often with Kagi Assistant in the files and firewalls we test:
- Assuming a robots.txt rule will stop Kagi Assistant. User-triggered fetches act for a person, and some operators say robots.txt may not apply to them. Check the operator's statement above.
- Blocking Kagi Assistant as if it were a bulk crawler. It fetches one page because a person asked; blocking it means that person's assistant cannot read your page.
- Counting Kagi Assistant visits as crawl volume. Each request maps to a real user question, which makes the paths it requests a useful signal of what people ask about you.
All three hide inside a file that looks correct, so check Kagi Assistant from outside after every change.
Spotting Kagi Assistant in your logs
robots.txt says what Kagi Assistant may do; your access logs show what it actually did.
Count requests
On a server with standard Nginx or Apache logs, this counts matching requests per day (adjust the log path for your host):
grep -iE "kagi-fetcher" /var/log/nginx/access.log \
| awk '{print $4}' | cut -d: -f1 | sort | uniq -cAnd this shows which paths it requested most, which is the quickest way to see whether your Disallow lines are being respected:
grep -iE "kagi-fetcher" /var/log/nginx/access.log \
| awk '{print $7}' | sort | uniq -c | sort -rn | head -20Check the requests are genuine
Anyone can send the Kagi Assistant user-agent, so confirm the source before acting on a match:
kagi-fetcher: we hold no published IP list, so use reverse DNS where the operator documents a hostname and treat an unverifiable Kagi Assistant request with caution.
Frequently Asked Questions
What user-agent string does Kagi Assistant use?
kagi-fetcher. Evidence that the spelling is in real use comes from our own robots.txt study: 26 of the 5,583 valid robots.txt files in the Tranco top 10,000 name it (fetched October 20, 2026), not from Kagi, which has not published crawler documentation naming it. Use it in robots.txt as the best available match, and treat a request carrying it as a clue rather than proof of who sent it.Is Kagi Assistant safe?
Will blocking Kagi Assistant hurt my SEO?
User-agent / Disallow: / without any SEO penalty.How do I block Kagi Assistant in robots.txt?
/robots.txt file:User-agent: kagi-fetcher Disallow: /
This instructs Kagi Assistant not to crawl any path on your site. To block only specific sections, replace / with the path (e.g.,
Disallow: /blog/).Does Kagi Assistant respect robots.txt?
kagi-fetcher will stop a client that chooses to honour it; for enforcement, add a firewall or CDN rule as well.How do I verify if Kagi Assistant is crawling my site?
kagi-fetcher (for example grep -i "kagi-fetcher" /var/log/nginx/access.log). Because the operator publishes no IP ranges or reverse-DNS pattern, a match shows that something used the name, not that Kagi sent it.