OpenAI launches Codex macOS app with multi-agent features

OpenAI has released a dedicated macOS application for its Codex AI coding tool, enhancing its capabilities to manage multiple AI agents for complex tasks. The app builds on Codex, which debuted last spring as a response to competitors like Anthropic's Claude Code. It introduces features like Skills and Automations to streamline workflows for developers.

OpenAI introduced the Codex macOS app on February 2, 2026, expanding access to its AI-powered coding assistant beyond command-line interfaces, web versions, and IDE extensions. Previously available since last spring, Codex began as a programming agent that generates code but has evolved to orchestrate multiple AI assistants working in parallel on intricate projects.

A key demonstration involved Codex creating a Mario Kart-like racing game, featuring selectable cars, eight tracks, and power-ups. "It took on the roles of designer, game developer and QA tester to validate its work by actually playing the game," OpenAI explained. The system delegated tasks, using GPT Image for visual assets while another model handled web game coding, showcasing how multi-agent collaboration tackles challenges beyond a single AI's scope.

The app includes a "Skills" section, which bundles instructions, resources, and scripts for reliable tool integration and workflow execution. Users can create and manage skills via a dedicated interface, explicitly requesting them or allowing automatic selection based on tasks. Additionally, the Automations feature enables scheduling repetitive jobs to run in the background. At OpenAI, this has been applied to tasks like daily issue triage, summarizing CI failures, generating release briefs, and bug checks.

Agents are organized by project, supporting multiple simultaneous efforts and worktrees to prevent conflicts. This launch positions OpenAI to catch up with Anthropic's Claude Code, which already offers a macOS version, amid broader industry experiments with multi-agent AI, such as Anysphere's Cursor building a web browser from scratch.

To boost adoption, OpenAI is doubling rate limits for Plus, Pro, Business, Enterprise, and Edu plans, while providing limited-time access to ChatGPT Free and Go users.

Liittyvät artikkelit

Illustration of OpenAI CEO Fidji Simo presenting the new desktop superapp integrating ChatGPT, Codex, and Atlas on a computer screen.
AI:n luoma kuva

OpenAI plans desktop superapp combining ChatGPT, Codex and Atlas

Raportoinut AI AI:n luoma kuva

OpenAI is developing a desktop superapp that merges its ChatGPT chatbot, Codex coding platform and Atlas browser to improve user experience. The initiative, led by applications CEO Fidji Simo, aims to simplify efforts amid a focus on core products. This follows recent announcements of smaller GPT-5.4 models.

Apple has released Xcode 26.3, enhancing its integrated development environment with deeper integration for AI coding agents like Claude and OpenAI's Codex. The update leverages the Model Context Protocol to allow these agents to access documentation, file structures, and project settings more effectively. This builds on AI features introduced in Xcode 26 at WWDC 2025.

Raportoinut AI

On February 5, 2026, Anthropic and OpenAI simultaneously launched products shifting users from chatting with AI to managing teams of AI agents. Anthropic introduced Claude Opus 4.6 with agent teams for developers, while OpenAI unveiled Frontier and GPT-5.3-Codex for enterprise workflows. These releases coincide with a $285 billion drop in software stocks amid fears of AI disrupting traditional SaaS vendors.

Apple is reportedly considering integration of third-party AI chatbots, such as ChatGPT and Gemini, into its CarPlay system. This move aims to expand AI accessibility in vehicles. The development was highlighted in a recent TechRadar article.

Raportoinut AI

OpenAI has introduced ChatGPT Library, allowing paid users to store, search and retrieve files uploaded or created within the AI chatbot. The feature automatically saves documents from chats and provides a central searchable hub. Access requires a Plus, Pro or Business subscription costing at least $20 per month.

Google has released Gemini 3.1 Pro, an updated version of its flagship AI model, emphasizing improvements in problem-solving and reasoning. The model is available in preview for developers and consumers starting today. It builds on the Gemini 3 release from November.

Raportoinut AI

Apple has selected Google's Gemini AI models to enhance its Siri virtual assistant in a forthcoming update. The decision, announced in a joint statement, marks a shift from previous integrations with OpenAI's ChatGPT. This multi-year partnership aims to deliver more capable AI experiences while upholding Apple's privacy standards.

 

 

 

Tämä verkkosivusto käyttää evästeitä

Käytämme evästeitä analyysiä varten parantaaksemme sivustoamme. Lue tietosuojakäytäntömme tietosuojakäytäntö lisätietoja varten.
Hylkää