ChatGPT-User — OpenAI's Live Fetch Agent
ChatGPT-User fetches web pages in real time when users ask ChatGPT to read a URL. Learn when to block or allow it in robots.txt.
QUICK FACTS
ChatGPT-User What is ChatGPT-User?
ChatGPT-User activates when a ChatGPT user asks the assistant to browse or read a specific URL. It is not a training crawler — it fetches pages on demand so ChatGPT can summarize, quote, or cite them in a conversation. This is also the user-agent used when ChatGPT users interact with external applications through GPT Actions.
How to Block ChatGPT-User
Add the following to your robots.txt file (located at the root of your website):
User-agent: ChatGPT-User Disallow: /
What Happens When You Block ChatGPT-User
ChatGPT will not be able to fetch your pages when a user asks it to browse a URL. Your site may still appear in ChatGPT Search results via OAI-SearchBot's index.
Should You Block ChatGPT-User?
ChatGPT-User is a user-triggered fetcher — it only activates when a real human asks the AI to read your page. It does not autonomously crawl your site. Blocking it prevents the AI from citing your content when users explicitly request it, which may reduce your referral visibility from OpenAI's products.
ChatGPT-User vs Other OpenAI Crawlers
OpenAI operates multiple crawlers, each serving a different purpose:
| User-agent | Purpose | Type |
|---|---|---|
| ChatGPT-User | Live page fetches triggered by ChatGPT users | User-Triggered Fetch |
| GPTBot | Collects training data for GPT models | AI Training |
| OAI-SearchBot | Indexes content for ChatGPT Search citations | AI Search Index |
Each crawler operates independently. Blocking ChatGPT-User does not block GPTBot or OAI-SearchBot — you must add a separate rule for each.
GENERATE YOUR ROBOTS.TXT
Use our visual generator to create a robots.txt file that blocks ChatGPT-User and any other crawlers you want to opt out of.
RELATED CRAWLERS