AI crawler · registry

cohere-ai

Cohere · Live retrieval · robots.txt token cohere-ai

honors robots.txtMeasured across 2,610 sites with a robots.txt policy record for this agent, out of 7,054 on record.
7%
of measured sites block it
178
sites blocking
2,432
sites allowing
yes
honors robots.txt

What it is definition

Retrieves pages to answer user-initiated prompts in Cohere's enterprise AI products.

cohere-ai is operated by Cohere and classified here as live retrieval. These agents fetch a single URL because a user asked about it. Disallowing one means the assistant answers from an older copy or from someone else's summary instead of the live page. Several are documented as not bound by robots.txt, because the request is user-initiated rather than a crawl.

Disallowing cohere-ai stops the fetch that happens when a user asks Cohere's enterprise products about one of your URLs. The answer still gets written, from an older copy or from a third party's description of the page, and you no longer control what it says.

robots.txt token
cohere-ai
Operator
Cohere
Purpose
Live retrieval
Honors robots.txt
yes
Documentation
https://knownagents.com/agents/cohere-ai

Identity on the wire exact string

User-agent string
Mozilla/5.0 (compatible; cohere-ai/1.0; +https://cohere.com)
Verify your own edge is not refusing it
curl -A 'Mozilla/5.0 (compatible; cohere-ai/1.0; +https://cohere.com)' https://example.com/

Replace the host with your own. A 403, a challenge page or an empty body means the edge is blocking the agent whatever robots.txt says.

How to allow it, how to block it robots.txt

Allow it
User-agent: cohere-ai
Allow: /

Absent any rule, the agent is already allowed, so this group only matters when your * group disallows something. Naming the agent replaces the * group for it entirely, so repeat here every disallow you still want to apply to it.

Block it
User-agent: cohere-ai
Disallow: /

Disallowing cohere-ai stops the fetch that happens when a user asks Cohere's enterprise products about one of your URLs. The answer still gets written, from an older copy or from a third party's description of the page, and you no longer control what it says.

Sites that block it 60 shown

DomainAI access scoreRank
amazon.com 33 26
yahoo.com 52 58
msn.com 34 62
amazonvideo.com 55 121
snapchat.com 63 125
nytimes.com 67 157
cnn.com 50 190
forbes.com 67 204
bbc.com 69 207
bbc.co.uk 70 226
launchpad.net 49 260
nature.com 56 281
weather.com 79 282
amazon.co.uk 33 318
ea.com 67 335
bloomberg.com 53 358
amazon.de 33 377
cnbc.com 59 457
amazon.co.jp 33 494
aol.com 54 499
ft.com 52 519
wired.com 74 533
usatoday.com 55 552
alrosa.ru 62 556
tripadvisor.com 50 564
uol.com.br 74 571
telegraph.co.uk 45 580
amazon.fr 33 609
sagepub.com 83 621
amazon.co.za 33 623
dailymail.co.uk 63 627
nintendo.com 59 628
techcrunch.com 79 629
amazon.ca 33 635
amazon.in 34 659
cnet.com 75 662
lemonde.fr 72 671
dailymail.com 63 681
primevideo.com 55 682
amazon.it 33 706
amazon.es 33 725
ted.com 63 726
bild.de 74 763
apnews.com 75 787
welt.de 65 800
people.com 38 801
amazon.com.au 33 812
theverge.com 68 815
nbcnews.com 63 823
amazon.com.br 33 833
lefigaro.fr 74 834
figma.com 80 869
investopedia.com 38 913
genius.com 60 926
repubblica.it 77 942
theatlantic.com 68 980
theconversation.com 52 1,019
huffpost.com 82 1,027
amazon.com.mx 33 1,032
spiegel.de 72 1,042

Compare Cohere

Cohere runs 2 agents in this registry, and they do different jobs. Blocking one says nothing about the others.

Common questions answered

Does blocking cohere-ai remove me from Cohere's enterprise products?

Partly. cohere-ai fetches a page only when a user asks about it, so disallowing it does not delist you from Cohere's enterprise products. It does mean the answer is composed without your live page, from a stale copy or a third-party summary.

How do I verify cohere-ai requests are genuine?

Cohere publishes neither reverse DNS names nor address ranges for cohere-ai, so a request carrying this user agent cannot be authenticated. The string is trivially spoofed and is routinely reused by unrelated scrapers. Treat it as a hint, rate-limit by source address, and do not grant it access you would not grant an anonymous client.

Check your own site free

See whether your robots.txt admits cohere-ai today, and whether your edge agrees with it.