Introducing the Codex app

Introducing the Codex app | OpenAI

February 2, 2026

Introducing the Codex app

Expanding what developers can do, with the new Codex app for macOS.

Loading…

Share

March 4, 2026 update: The Codex app is now available on Windows.

Today, we’re introducing the Codex app for macOS—a powerful new interface designed to effortlessly manage multiple agents at once, run work in parallel, and collaborate with agents over long-running tasks.

We're also excited to show more people what's now possible with Codex⁠. For a limited time we're including Codex with ChatGPT Free and Go, and we're doubling the rate limits on Plus, Pro, Business, Enterprise, and Edu plans. Those higher limits apply everywhere you use Codex—in the app, from the CLI, in your IDE, and in the cloud.

The Codex app changes how software gets built and who can build it—from pairing with a single coding agent on targeted edits to supervising coordinated teams of agents across the full lifecycle of designing, building, shipping, and maintaining software.

The Codex app: A command center for agents

Since we launched Codex in April 2025, the way developers work with agents has fundamentally changed. Models are now capable of handling complex, long-running tasks end to end and developers are now orchestrating multiple agents across projects: delegating work, running tasks in parallel, and trusting agents to take on substantial projects that can span hours, days, or weeks. The core challenge has shifted from what agents can do to how people can direct, supervise, and collaborate with them at scale—existing IDEs and terminal-based tools are not built to support this way of working.

This new way of building coupled with new model capabilities demands a different kind of tool, which is why we are introducing the Codex desktop app, a command center for agents.

Work with multiple agents in parallel

The Codex app provides a focused space for multi-tasking with agents. Agents run in separate threads organized by projects, so you can seamlessly switch between tasks without losing context. The app lets you review the agent’s changes in the thread, comment on the diff, and even open it in your editor to make manual changes.

It also includes built-in support for worktrees, so multiple agents can work on the same repo without conflicts. Each agent works on an isolated copy of your code, allowing you to explore different paths without needing to track how they impact your codebase. As an agent works, you can check out changes locally or let it continue making progress without touching your local git state.

The app picks up your session history and configuration from the Codex CLI and IDE extension, so you can immediately start using it with your existing projects.

Go beyond code generation with skills

Codex is evolving from an agent that writes code into one that uses code to get work done on your computer. With skills⁠, you can easily extend Codex beyond code generation to tasks that require gathering and synthesizing information, problem-solving, writing, and more.

Skills bundle instructions, resources, and scripts so Codex can reliably connect to tools, run workflows, and complete tasks according to your team’s preferences. The Codex app includes a dedicated interface to create and manage skills. You can explicitly ask Codex to use specific skills, or let it automatically use them based on the task at hand.

We asked Codex to make a racing game, complete with different racers, eight maps, and even items players could use with the space bar. Using an image generation skill⁠(powered by GPT Image) and a web game development skill⁠, Codex built the game by working independently using more than 7 million tokens with just one initial user prompt. It took on the roles of designer, game developer, and QA tester to validate its work by actually playing the game.

We’ve included the game, as well as the prompt and skills used to create it, below. You can also try out earlier iterations to see how Codex improved it as it worked for longer.

The game was created by Codex with the develop-web-game skill using this prompt that we've summarized for clarity:

Implement Voxel Velocity as a 3D voxel kart racer using Three.js, with exactly one mode: Single Race (always 3 laps, 1 human vs 7 CPU, and all 8 tracks available immediately with no progression). Build a minimal pre-race flow with only: Track (8), Character (8), Difficulty (Chill/Standard/Mean), optional Mirror Mode, optional Allow Clones, and Start Race, plus an Options menu and an in-race pause menu (Resume / Restart / Quit). Create an arcade driving model with responsive handling, forgiving glancing wall hits, meaningful drifting as the main skill, and a drift-charge system that produces exact boost tiers (Tier 1 0.7s, Tier 2 1.1s, Tier 3 1.5s) while keeping baseline speed “fast-but-readable” and pack passing constant on wide roads. Implement exactly 8 items with one-item capacity, subtle position-weighted distribution, and mild effects (max loss of control ≤1.2s, max steering disabled ≤0.6s) that create goofy chaos without hard stuns, plus off-road slowdowns that are reduced by 50% during boosts. Define the 8 characters with their given stats and AI tendencies, implement CPU difficulty presets and track-authored racing/variation splines, drift zones, and hazard avoidance so AI uses multi-lane width for clean overtakes, and ship HUD/audio essentials (position, lap/final lap banner, minimap, item slot, timer/splits, readable SFX, and one music loop per track).

Codex was then continuously reprompted from a random list of ten generic prompts to keep working on the problem. An example of one of the prompts is:

Your job is to add new features so the game matches the original more closely. First, play the game and identify what’s missing vs. the original. Then pick a few missing features and implement them. After each feature, thoroughly test it by playing the game and confirm it works. If you notice any bugs while playing, prioritize fixing them too.

At OpenAI, we’ve built hundreds of skills internally to help multiple teams confidently delegate work to Codex that would otherwise be hard to define consistently—from running evals and babysitting training runs to drafting documentation and reporting on growth experiments.

The Codex app includes a library of skills for tools and workflows that have become popular at OpenAI, with a few highlighted below. You can find the…