Codex-CLI
Codex-CLI is an AI coding tool operated by OpenAI. Developers use it to write, debug, or understand code, and it visits the web to fetch documentation, package metadata, code samples, or related references.
Visits are user-initiated. A developer types a question or pastes a URL and Codex-CLI retrieves it on their behalf. You will not see scheduled crawling, just bursts that follow user activity.
Allowing this agent makes your developer documentation available to a much larger audience than just the people who land on your site directly. Your docs end up inside the IDE.
See Codex-CLI on your own site
Match the User-Agent header on incoming requests against the pattern below.
regex
For higher confidence, also verify the source IP against the operator's published ranges. UA strings can be spoofed; IP ownership is harder to fake.
Renders JavaScript
Sometimes
IP verification
Published IP ranges
Crawl frequency
Burst, user-driven
Honors robots.txt
Yes
Honors Crawl-delay
Varies
OpenAI runs 17 bots in total. Each one is a separate user-agent so you can allow or block them independently.
Agentic Browser
8Live-Fetch AI
2Agentic Commerce
2AI Search Index
1AI Coding Tool
1- Codex-CLIYou are here
Link Unfurler
1Should I let Codex-CLI through?
In most cases, yes. Lets your developer documentation reach a much larger audience inside the IDE. If volume gets noisy, rate-limit it before you block it outright.
Does blocking Codex-CLI affect my Google rankings?
No. Codex-CLI fetches a page only when a user is actively asking OpenAI a question. It has nothing to do with how Google or Bing rank you. The cost of blocking is that OpenAI can't quote your content in its answer.
How do I confirm a request is really from Codex-CLI?
Two checks. The User-Agent header should match a known Codex-CLI string, and the request's source IP should fall inside OpenAI's published ranges. The User-Agent alone is trivially spoofable, so the IP check is what gives you confidence. OpenAI publishes the ranges so you can validate at the CDN or edge.
Does a Codex-CLI visit count as a real user visit?
Sort of. There is a human asking OpenAI a question on the other end, but they never load your page in their own browser. They see whatever OpenAI quotes back, usually a snippet plus a citation link. Count it as upstream attention rather than as a session.
How is Codex-CLI different from OpenAI's other bots?
OpenAI splits work across multiple user-agents so site owners can decide on each one independently. Training crawlers, live-fetch agents, search indexers, and agentic browsers each get their own name. Worth scanning the rest of the OpenAI family above to see which ones actually matter for your site.
What's the cleanest way to control Codex-CLI?
Two layers. Robots.txt for the polite crawlers that read it, and rules at your CDN or edge for the ones that don't. Rankly's Agent Experience handles both from a single config, so you can allow, block, rate-limit, or serve a stripped-down version per bot. Agent Analytics handles the observation half so you know which bots are actually worth a rule.
Verify everything above against the operator's own documentation.