Google-Agent
A user-triggered fetcher Google added to its documentation on 20 March 2026 for agents that run on Google infrastructure and browse on a person's behalf, Project Mariner among them. It carries a Chrome-like user-agent string with the token inside it and publishes its own range file, user-triggered-agents.json, separate from the other fetcher feeds.
What Google-Agent means
Google classes it as a user proxy, so it generally ignores robots.txt.
What Google-Agent does not show
It is the concrete case where the caveat on user-triggered fetch stops being theoretical: a rule addressed to it is a request the fetcher is documented not to read.
Where Google-Agent comes up on this site
- AI agents acting for people: 613 verified visits, one read robots.txtWhen a person asks an assistant about a page, the assistant sends a fetcher to read it: ChatGPT-User for OpenAI, Claude-User for Anthropic, Perplexity-User for Perplexity, Google-Agent for agents hosted by Google.
Terms this definition uses
user-triggered fetch · token · robots.txt
Related terms in Crawlers and access
Who is fetching, whether they are who they claim, and what your rules actually permit.
visitor resolve · published crawler ranges · operator origin · signed agent · agent arrival · agent conduct record · agent traffic index · user-triggered fetch exemption · retrieval crawler · user-triggered fetch · verified crawler · forged crawler identity · unverifiable · robots.txt · user-agent group · AI opt-out · Content-Signal · crawl budget · cloaking · challenge page at 200 · uniform refusal · nonexistent-path control · blocked render resource · off-host redirect · homepage refused · FCrDNS · Crawler trap · Conditional request · ASN blocking · operator feed · residential proxy · Google-Extended · GPTBot vs OAI-SearchBot · ClaudeBot vs Claude-User · PerplexityBot vs Perplexity-User · CCBot · Bytespider · agentic traffic · crawler classification · user agent · datacenter IP · vantage point · rate limit · delivery comparison · honeypot
Questions about Google-Agent
What is Google-Agent?
A user-triggered fetcher Google added to its documentation on 20 March 2026 for agents that run on Google infrastructure and browse on a person's behalf, Project Mariner among them. It carries a Chrome-like user-agent string with the token inside it and publishes its own range file, user-triggered-agents.json, separate from the other fetcher feeds.
What does Google-Agent not show or guarantee?
It is the concrete case where the caveat on user-triggered fetch stops being theoretical: a rule addressed to it is a request the fetcher is documented not to read.
Which area of the glossary does Google-Agent belong to?
Crawlers and access: Who is fetching, whether they are who they claim, and what your rules actually permit.
← Google-Extended · GPTBot vs OAI-SearchBot →
See it in the full glossary · 751 terms across 19 areas.