OAI-SearchBot: OpenAI's search crawler
OAI-SearchBot is the crawler OpenAI uses to find pages and show them in ChatGPT's search answers.
Picked is an AI visibility tool for agencies and B2B SaaS teams. It asks ChatGPT, Claude, Gemini, Perplexity and Google's AI answers the prompts your buyers ask, records which brands and pages they name, and writes the article built to become the source they quote.
At a glance
OAI-SearchBot in one table
- Company
- OpenAI
- What it's for
- Search index: read into the index an ai assistant searches.
- robots.txt token
OAI-SearchBot- Full user agent
Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36; compatible; OAI-SearchBot/1.4; +https://openai.com/searchbot- Follows robots.txt
- Follows it. A site that blocks it doesn't appear in ChatGPT's search answers, though OpenAI says it can still show up as a navigational link.
- How to verify
- Check the visitor's IP against the list OpenAI publishes. A request outside it isn't OAI-SearchBot, whatever its user agent says. The IP list
- Source
- OpenAI's documentation, read on October 12, 2026.
What to know
OAI-SearchBot, in practice
OAI-SearchBot is the OpenAI agent to protect. OpenAI says a site that blocks it doesn't appear in ChatGPT's search answers, and that it's the name to use in robots.txt to opt out of search: ChatGPT-User doesn't decide that.
It reads ahead of any question, so on our own site it was OpenAI's busiest agent by far. If it's missing from your logs while GPTBot shows up, look at your CDN or firewall before robots.txt: an AI bot setting can turn it away while the file allows it.
The pages it indexes are the ones ChatGPT can cite, and ChatGPT tags the clicks it sends from them with utm_source=chatgpt.com, so the visits they bring can be counted.
Real data
What OAI-SearchBot read on a real site
LaunchOn.it, our own launch platform, tracked in Picked through Cloudflare from September 12 to October 11, 2026. One site, so read it as an example, not an average.
10,900
Requests in 30 days
1,441
Different pages read
30 of 30
Days it came
100%
Verified by Cloudflare as the real bot
97% of its requests got a page back; 1% hit an address that doesn't exist.
- /products/25%
- /tech/7%
- /categories/7%
- /country/4%
- /_next/image4%
By the first folder of the address. /_next/ holds the site's scripts and images.
robots.txt
Allow OAI-SearchBot
Allow it. It builds the index OpenAI's answers are drawn from, so blocking it means those answers can't cite your pages.
User-agent: OAI-SearchBotAllow: /Needed only if a wider rule blocks it: robots.txt lets every bot in by default. A bot named in its own group ignores the User-agent: * group, so repeat your private paths there as Disallow lines. A block in your CDN or firewall has to be lifted there.
A rule only changes what the bot reads next. To see whether OAI-SearchBot reads your pages now, and which ones, track AI crawlers on your server or see the full AI crawler list.
Questions
Frequently asked questions
From OpenAI's documentation, read on October 12, 2026.
OAI-SearchBot is the crawler OpenAI uses to find pages and show them in ChatGPT's search answers.
A site that blocks it doesn't appear in ChatGPT's search answers, though OpenAI says it can still show up as a navigational link.
Check the visitor's IP against the list OpenAI publishes. A request outside it isn't OAI-SearchBot, whatever its user agent says.
Allow it. It builds the index OpenAI's answers are drawn from, so blocking it means those answers can't cite your pages.
Find out what ChatGPT and Google AI say about you
Add your domain and the prompts your buyers ask. Unlimited seats for your whole team, and no promises we can't keep.