User-triggered fetch
ChatGPT-User: what it is.
ChatGPT-User is the agent OpenAI uses for certain actions a person takes in ChatGPT and Custom GPTs.
Identity
- Operator: OpenAI
- User-agent token:
ChatGPT-User - robots.txt token:
ChatGPT-User - In Geordy's crawler directory: Fetches one page because a ChatGPT user followed a link. See the full list.
What it does, per OpenAI
OpenAI says ChatGPT-User is used for certain user actions in ChatGPT and Custom GPTs.
OpenAI says it is not used for crawling the web in an automatic fashion.
OpenAI says that because these actions are user-initiated, robots.txt rules may not apply to it.
OpenAI says ChatGPT-User does not determine whether content appears in Search.
robots.txt
Allow ChatGPT-User
User-agent: ChatGPT-User
Allow: /Block ChatGPT-User
User-agent: ChatGPT-User
Disallow: /OpenAI names ChatGPT-User as the robots.txt token. Its page does not print example lines, so the ones below are standard robots.txt syntax around that token.
OpenAI says robots.txt rules may not apply to this agent, so a Disallow line is not a guarantee that it will not fetch a page.
To manage whether your site appears in ChatGPT search, OpenAI points to OAI-SearchBot, not ChatGPT-User.
What Geordy observes
Share of eligible sites where ChatGPT-User requested each Geordy-served file at least once, over the 90 days to 12 November 2026.
| Format | Evidence | Sites with a request | Median requests per site per day | Rank |
|---|---|---|---|---|
| Markdown | Established pattern | under 5% | 0 | Similar to others |
| Schema JSON (JSON-LD) | Established pattern | under 5% | 0 | Similar to others |
| YAML | Established pattern | about 5% | 0 | Similar to others |
| RSS Feed | Established pattern | under 5% | 0 | Similar to others |
| OG.json | Established pattern | 0% | 0 | Similar to others |
| LLMs.txt | Established pattern | 0% | 0 | Similar to others |
| Humans.txt | Established pattern | 0% | 0 | Similar to others |
| Manifest.json | Established pattern | 0% | 0 | Similar to others |
Figures are rounded and cover only sites that served the file for the whole window. Requests are to Geordy-served files, identified by user agent; a request is not evidence of use or citation. Pairs with too few independent sites are not shown. See how we measure.
Check your site
See whether your robots.txt currently allows or blocks ChatGPT-User, and what else AI crawlers find on your site.
Sources
Last reviewed: 19 October 2026. Every statement about what ChatGPT-User does comes from the operator's own documentation: