ChatGPT Agent
ChatGPT Agent is a bot operated by OpenAI that browses the web on its own to finish multi-step tasks. ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It honours robots.txt, and a request claiming to be ChatGPT Agent can be checked against a published IP range file.
ChatGPT Agent at a glance
| User agent | ChatGPT AgentToken only. The operator has not published a full user-agent string, so match on the substring rather than an exact header. |
|---|---|
| Operator | OpenAI |
| Purpose | Autonomous agents |
| Respects robots.txt | Yes, documented |
| Verification method | Published IP range file OpenAI publishes one range file per bot. Use the file listed against this agent in the bots documentation, not the GPTBot file. https://platform.openai.com/docs/bots |
| Crawl pattern | Not published |
| Robots.txt tokens | ChatGPT Agent |
| Operator documentation | https://platform.openai.com/docs/bots |
ChatGPT Agent is an AI agent created by OpenAI that can use a web browser. It can intelligently navigate and interact with websites to complete multi-step tasks on behalf…
Allow or block ChatGPT Agent
Paste one of these into the robots.txt file at the root of your domain. Rules are per token, so a block on one crawler leaves every other bot untouched.
User-agent: ChatGPT Agent
Disallow: /Blocks every path for this crawler only.
User-agent: ChatGPT Agent
Allow: /Explicit allow. Useful when a wildcard rule above it would otherwise catch this crawler.
User-agent: ChatGPT Agent
Allow: /
Disallow: /account/
Disallow: /checkout/
Disallow: /searchEdit the Disallow paths to match your own account, checkout and search URLs.
What blocking actually costs you
Blocking ChatGPT Agent stops automated sessions that fill forms, click through flows and read pages the way a logged-in user would. Rate limits and challenges usually work better here than a robots.txt line.
Block every crawler in the directory at onceIs that really ChatGPT Agent?
A user-agent header is a string the client chooses. Scrapers copy ChatGPT Agent precisely because site owners allow it. OpenAI publishes one range file per bot. Use the file listed against this agent in the bots documentation, not the GPTBot file.
Paste the IP address from your access log below. You will see whether it belongs to a hosting provider, a residential proxy pool or a Tor exit, plus the ASN that announces it, which is what tells you whether the claim holds up.
Other crawlers run by OpenAI
Related crawlers
Identify crawlers automatically instead of by hand
Agentscan checks a request against published crawler ranges, reverse DNS and hosting data, then returns a verdict your edge can act on. One call per request, no range files to keep up to date.