Agent-Readiness Grade / Crawlers / OAI-SearchBot

OAI-SearchBot

OpenAI · search. Source: https://platform.openai.com/docs/bots, read 2026-09-29. Where the vendor page does not state a fact, this page says "not published".

Facts from the vendor page

Operator OpenAI

What it is for Search crawler. OpenAI uses it to surface websites in ChatGPT's search features; sites that opt out are not shown in ChatGPT search answers, though they can still appear as navigational links. A robots.txt change takes about 24 hours to be reflected.

Published user-agent string 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
Example string from the vendor page; the version number may change. A variant carrying a "robots.txt" marker is used when fetching robots.txt.

Honors robots.txt Yes. OpenAI recommends allowing OAI-SearchBot in robots.txt (and its published IP ranges) for a site to appear in ChatGPT search results; the tag is independent of GPTBot.

Verification (IP ranges or reverse DNS) Published IP ranges at https://openai.com/searchbot.json.

robots.txt token OAI-SearchBot

Operator	OpenAI
What it is for	Search crawler. OpenAI uses it to surface websites in ChatGPT's search features; sites that opt out are not shown in ChatGPT search answers, though they can still appear as navigational links. A robots.txt change takes about 24 hours to be reflected.
Published user-agent string	`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` Example string from the vendor page; the version number may change. A variant carrying a "robots.txt" marker is used when fetching robots.txt.
Honors robots.txt	Yes. OpenAI recommends allowing OAI-SearchBot in robots.txt (and its published IP ranges) for a site to appear in ChatGPT search results; the tag is independent of GPTBot.
Verification (IP ranges or reverse DNS)	Published IP ranges at https://openai.com/searchbot.json.
robots.txt token	`OAI-SearchBot`

robots.txt lines

To allow OAI-SearchBot explicitly (so your policy survives a change to the User-agent: * group):

User-agent: OAI-SearchBot
Allow: /

To block it:

User-agent: OAI-SearchBot
Disallow: /

What Agent-Readiness Grade checks for OAI-SearchBot

The crawler-access area parses your robots.txt by user-agent group and reports OAI-SearchBot as allowed, disallowed or unmentioned (unmentioned means allowed by default). A group for "OAI-SearchBot" wins over the "*" group; "Disallow: /" or "Disallow: /*" without a matching "Allow: /" counts as blocked; narrower path rules are reported as partial. OAI-SearchBot is one of the 8 tokens in that score (GPTBot, ClaudeBot, OAI-SearchBot, PerplexityBot, Google-Extended, Amazonbot, CCBot, Bytespider).

Context: in the 30-day census of one Cloudflare zone (2026-08-29 to 2026-09-28), 2,197 requests carried a user agent matching "OAI-SearchBot". See the census report.

Other crawlers

GPTBot · ChatGPT-User · ClaudeBot · Claude-User · PerplexityBot · Google-Extended · Amazonbot · CCBot · Bytespider

Free agent-readiness checkers are a crowded category: Goodie, Frase, aiwebreadiness.com, Arobis, Rank Prompt, Otterly and Writesonic each offer one. Of the checkers we looked at, Agent-Readiness Grade is the only one we found that grades payment and agent-checkout surfaces (/.well-known/x402, agent-card.json, mcp-registry-auth, openapi.json, the MCP endpoint) and legal notices. Statement dated 2026-09-29.