Browsing agent from Google
Gemini in Chrome (auto browse)
In short
Gemini in Chrome (auto browse) is Google's browsing agent. Gemini in Chrome has no robots.txt token, so robots.txt cannot address it and the crawl cannot measure a block rate. The operator publishes nothing a site can check. Verisoul reports caps of 20 tasks a day on AI Pro and 200 on Ultra.
- Operator
- Purpose
- Task agent All task agent rows. A browsing agent that clicks, fills forms and finishes a job for a person.
- User-agent string
- No exact string is published. What the operator or a third party says: The user's own Chrome user agent; no marker in local mode
- robots.txt token
- None. No robots.txt line can address this agent.
- Respects robots.txt
No documentation
operator publishes no bot documentation (checked 2026-11-04) for auto browse in the user's own Chrome; Google's cloud agents declare Google-Agent instead. Source, read 2026-11-04.
- Verification
Nothing published
The operator publishes no list, reverse DNS pattern or key directory a site owner can check. Documentation, read 2026-11-04.
- IP ranges
- Not published.
- Rate behaviour
- Verisoul reports caps of 20 tasks a day on AI Pro and 200 on Ultra.
- Block rate
-
None: the agent has no token, so a robots.txt block rate does not exist.
- Documentation
- Operator publishes no bot documentation (checked 2026-11-04). Closest page read.
Note. Auto browse launched 2026-01-28 as a US preview for AI Pro and Ultra subscribers, per Verisoul (secondary). It hands control back to the person to pay or accept terms.
Allow and refuse lines
This agent has no robots.txt token, so there are no lines to copy. Without a token, a published list or a signature, a site owner cannot tell it from an ordinary visitor by request alone.
Refusing or allowing in robots.txt states a preference. For this row the operator or its documentation says robots.txt may not govern the fetch, so enforcement belongs in your WAF.
Google in the Verification Ledger
Five IP lists, reverse DNS for every class, and an experimental key directory for Google-Agent. Nothing for auto browse in the user's Chrome. All operators.
- IP lists
- developers.google.com/static/search/apis/ipranges/googlebot.json
- developers.google.com/static/search/apis/ipranges/special-crawlers.json
- developers.google.com/static/search/apis/ipranges/user-triggered-fetchers.json
- developers.google.com/static/search/apis/ipranges/user-triggered-fetchers-google.json
- developers.google.com/static/search/apis/ipranges/user-triggered-agents.json
- Reverse DNS
- crawl-*.googlebot.com, geo-crawl-*.geo.googlebot.com, rate-limited-proxy-*.google.com, *.gae.googleusercontent.com, google-proxy-*.google.com
- Key directory
- https://agent.bot.goog/.well-known/http-message-signatures-directory (Google-Agent, subset of requests, experimental)
- Cloudflare
- not checked
- Visa TAP registry
- no public operator-level registration found (checked 2026-11-04)
- Mastercard Agent Pay
- no public operator-level registration found (checked 2026-11-04)
Other Google rows
- Googlebot Search index
- Google-Extended (control token) Training
- Google-CloudVertexBot Other
- GoogleOther Other
- Storebot-Google Search index
- Google-Agent Task agent
- Google-GeminiNotebook (was Google-NotebookLM) Live answer fetch
Sources
Last reviewed 2026-11-04