Skip to content

Agent · OpenAI

ChatGPT-Agent

The browser behind ChatGPT agent mode, which navigates sites and completes tasks for one user. It renders pages in a real browser but does not execute third-party analytics, so it is invisible to JavaScript-based measurement.

Operator
OpenAI
Feeds
ChatGPT (agent)
robots.txt token
ChatGPT-Agent
Honours robots.txt
Honours robots.txt
Documentation
platform.openai.com

What it looks like in server logs

A representative user-agent string. Version numbers change; the ChatGPT-Agent token does not. Paste your own log line into the user-agent checker to confirm a match.

user-agent
Mozilla/5.0 (compatible; ChatGPT-Agent/1.0; +https://openai.com/bot)

How to block ChatGPT-Agent

Add this to the robots.txt at the root of your domain. Robots.txt is advisory: it works only on crawlers that choose to read it. This one is honours robots.txt according to its operator.

robots.txt
User-agent: ChatGPT-Agent
Disallow: /

To block every agentic browser at once, or to block training while keeping AI search citations, use the robots.txt generator.

How to allow ChatGPT-Agent while blocking others

A more specific User-agent group wins over a wildcard. Place this above any User-agent: * block that disallows paths, and ChatGPT-Agent keeps full access.

robots.txt
User-agent: ChatGPT-Agent
Allow: /

How to verify a genuine hit

The user-agent string is self-asserted: anyone can send it from a laptop, and scrapers routinely impersonate well-known crawlers to slip past filters aimed at unknown ones.

OpenAI publishes its IP ranges as JSON; a hit from outside them is spoofed.