Agent Ready Crawlers

The field guide to every AI crawler and agent at the door, and the vendors who decide who gets in.

Crawler operator

xAI

In short

xAI gives Grok Bot an always-on cloud computer of its own, shared by an account's other Bots, and lets it hand control back to the user at a CAPTCHA or a passkey. A site learns little about it: neither x.ai nor grok.com serves a key directory, and a third party saw signing end in mid-October.

Type
Crawler operator
Homepage
x.ai
In one line
xAI operates Grok Bot, an agent product in which each Bot works on a persistent cloud computer with a browser; xAI's docs give site owners no user agent, IP list or signing keys for that traffic.
Last read
2026-11-05

What xAI does for this layer

From the vendor's own pages

xAI's docs say each Grok Bot works on a persistent cloud computer with a browser, filesystem and terminal, and keeps working while the user's laptop is closed. (docs.x.ai) xAI includes Grok Bot with the Premium, Super and Ultra tiers of The X Subscription and with paid individual plans on legacy Cursor plans. (docs.x.ai) xAI says all Bots on one account share a single cloud computer, including browser cookies, signed-in sessions and files. (docs.x.ai) Grok Bot hands the computer back to the user for steps it cannot finish, which xAI lists as single sign-on, passkeys, approvals on another device and "A CAPTCHA it couldn't get past". (docs.x.ai)

Grok Bot can pay at checkout with a card saved in its Vault, a card entered in a Secure Form, or a connected wallet such as Link or X Money. (docs.x.ai) xAI's API web_search tool lets developers limit browsing with allowed_domains or excluded_domains, up to five domains each. (docs.x.ai)

Reported by a third party

Verisoul reported on 2026-11-03 that Grok Bot stopped signing requests with Web Bot Auth in mid-October 2026 and routes its cloud browser traffic through a reverse proxy on the user's own device, so sites see the user's IP. (verisoul.ai, dated 2026-11-03)

What our crawl saw

The Web Bot Auth key directory path returned HTTP 404 on both x.ai and grok.com on 2026-11-05. (x.ai)

Products and plans

ProductWhat it doesPrice modelFromAs of
Grok Bot Always-on agent product; each Bot browses and acts from a persistent cloud computer. No price recorded
Web Search tool (xAI API) Server-side search and browsing tool for API callers, with domain allow and exclude filters. No price recorded

Standards

StandardStatusEvidence
RFC 9309 (robots.txt) No statement xAI's docs index lists no crawler or robots.txt page (read 2026-11-05).
Web Bot Auth No statement No key directory on x.ai or grok.com (observed 404, 2026-11-05).
Published IP list No statement No IP list in xAI's docs (read 2026-11-05).

Our checks

CheckResultMethodDate
Homepage fetch HTTP 403 GET with the crawl user agent after a robots.txt check 2026-11-05
Web Bot Auth key directory 404 on x.ai and grok.com GET /.well-known/http-message-signatures-directory with the crawl user agent 2026-11-05

What xAI does not do

  • xAI publishes no robots.txt token for any crawler or fetcher in its docs index.

Sources

Last reviewed 2026-11-05