OpenAI Launches Codex App for macOS to Manage Multi-Agent Coding

Feb 3, 2026
OpenAI has released the Codex app for macOS, a new desktop interface that allows developers to manage multiple coding agents simultaneously, according to the company. The app integrates with existing Codex tools and introduces features like Automations, customizable personalities, and secure sandboxing.

OpenAI has introduced the Codex app for macOS, announced in a press release, expanding its suite of tools for agent-based software development. The app provides a unified interface for managing multiple AI coding agents, allowing developers to run tasks in parallel and collaborate with agents on long-running projects.

The Codex app integrates with existing Codex environments, including the CLI and IDE extensions, and supports multi-agent workflows organized by project threads. Developers can review and comment on code changes, manage worktrees to prevent conflicts, and switch between agents without losing context. Built-in security features use open-source sandboxing to restrict agent access and enforce permission rules.

Codex now supports "skills"—bundled sets of instructions, scripts, and resources that extend the system beyond code generation to tasks like documentation, design translation, and deployment. Users can create and share these skills within teams, enabling Codex to automate workflows across tools such as Figma, Linear, and Vercel.

The app also introduces Automations, which let Codex perform scheduled tasks in the background, and personality settings that adjust how the agent communicates. Available immediately on macOS, the Codex app is included with ChatGPT Plus, Pro, Business, Enterprise, and Edu subscriptions, with temporary access extended to Free and Go users.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief or AI Programming Weekly.

Also, consider following us on social media:

Free newsletter

AI Programming Weekly

Weekly news about AI tools for software engineers, AI enabled IDE's and much more.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.