AI Glossary · OpenAI

OpenAI Codex app

Also known as: Codex, Codex desktop app

Definition

The OpenAI Codex app is a desktop application for macOS and Windows that acts as a command center for AI coding agents — running multiple agents in parallel, using background computer use to operate your apps, and automating routine engineering work with reusable skills.

Codex began as OpenAI's coding model and grew into a full agentic platform. The desktop app is built around parallelism: rather than one assistant you chat with, it orchestrates many agents at once, each in its own isolated environment, so long-running work compresses into less time.

Its standout features are multi-agent orchestration, background computer use (the agent sees, clicks, and types with its own cursor), Automations for recurring work, and Skills that align the agent to a team's standards. Much of its execution runs in OpenAI's cloud and it is deeply GitHub-native, which makes it especially strong for software engineering.

Want to actually use this, not just define it?

I train business teams to put agentic AI to work in their real workflows — live, in a single session.