Check my connection

AI & bot directory · AI assistant fetch

cohere-ai: what it is, how to verify it and how to block it

cohere-ai is run by Cohere. Cohere has published no documentation we could read; community lists describe it as fetching pages to answer users' prompts.

Key facts

Key facts
Operator
Cohere
Category
AI assistant fetch
robots.txt name
cohere-ai
Follows robots.txt
Couldn't check: Not documented
Can it be verified?
Couldn't check: No, user agent only
Official documentation
Cohere has published none we could read. The user-agent name comes from the community lists ai.robots.txt and crawler-user-agents.
Registry checked
Nov 11, 2026

Cohere publishes no documentation for cohere-ai that we could read. What we know comes from community lists, so treat it as unconfirmed.

User agent

Its name in robots.txt is cohere-ai.

Community lists recognise it by cohere-ai in the user agent.

Can you verify cohere-ai?

No No addresses are published, and there is no operator documentation, so any visitor can claim to be cohere-ai. Treat its user agent as a claim.

Check an address from your logs

Does cohere-ai follow robots.txt?

Not documented We don't know: Cohere hasn't said so anywhere we could read. robots.txt may or may not keep it out.

How to block or allow cohere-ai

To ask it to stay away from the whole site, add this to robots.txt:

User-agent: cohere-ai
Disallow: /

To keep it out of one folder only:

User-agent: cohere-ai
Disallow: /private/

To allow it while asking every other bot to stay away:

User-agent: cohere-ai
Allow: /

User-agent: *
Disallow: /

robots.txt is a request, not a lock. To enforce a block, add a firewall or CDN rule that matches cohere-ai in the user agent. That stops the real cohere-ai; a bot that lies about its user agent can still get through.

To build one robots.txt for several bots at once, use the robots.txt generator.

How often does cohere-ai visit?

Cohere doesn't publish how often cohere-ai visits a site, and iplover doesn't see your traffic. Your own access log is the only reliable count: paste it into the log checker, which counts each crawler's visits and flags fakes, in your browser.

Official documentation

Cohere has published none we could read. The user-agent name comes from the community lists ai.robots.txt and crawler-user-agents.

Registry checked Nov 11, 2026. The address lists are downloaded every 6 hours.