# OAI-SearchBot

OpenAI's crawler: what it does, robots.txt handling per the operator, and observed behaviour on this property.

- Operator: OpenAI
- Purpose: AI search index | operator's words: "used to surface websites in search results in ChatGPT's search features"
- robots.txt token: `OAI-SearchBot`
- Appears in access logs: yes
- 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`
- robots.txt: Honors robots.txt. OpenAI documents the token so sites can opt out of ChatGPT search. Blocking it removes a site from ChatGPT's search results, not from model training; that is GPTBot's token.
- IP list: https://openai.com/searchbot.json
- Verification: Match the requesting IP against the published list.
- Documentation: https://developers.openai.com/api/docs/bots (read 2026-08-04)

Block it:
```
User-agent: OAI-SearchBot
Disallow: /
```

Observed on this property (logged since 2026-08-04):
- First seen 2026-08-04, most recent 2026-08-04
- Requests: 2 in the last 30 days, 2 all time, of which 2 for /robots.txt
- 2x `/robots.txt`

---

Source: https://agentvisibilitytools.com/crawlers/oai-searchbot/ · HTML version of this page.
Full index: https://agentvisibilitytools.com/agents.md · JSON: https://agentvisibilitytools.com/api/tools
Free to quote with attribution to The Agent Visibility Directory, https://agentvisibilitytools.com.