Codex Can Now Use Your Mac While You Work
OpenAI's Codex desktop app adds background computer use on macOS, an in-app browser, image generation via gpt-image-1.5, and 90+ new plugins.
On April 16, 2026, OpenAI released a major update to Codex that pushes the desktop app beyond code generation into general computer operation. Codex can now see, click, and type across macOS applications using its own cursor, run an in-app browser, generate images with gpt-image-1.5, and connect to over 90 new plugins. More than 3 million developers use Codex weekly, and this update positions the tool as a workspace for getting professional work done, not just writing code.
Background Computer Use
The headline feature is background computer use on macOS. Codex operates apps by seeing the screen, clicking, and typing with its own cursor. Multiple agents can work in parallel without interfering with the user’s active work in other applications. For developers, this enables frontend iteration, native app testing, simulator flows, and GUI-only bug fixes.
Computer use is initially available on macOS. It is not available at launch in the European Economic Area, the United Kingdom, or Switzerland.
In-App Browser and Image Generation
The Codex app now includes an in-app browser where users can open local or public pages and comment directly on rendered content to provide precise instructions. This is immediately useful for frontend and game development. OpenAI plans to expand browser capabilities beyond localhost over time.
Codex also integrates gpt-image-1.5 for generating and iterating on images within the same workflow. Combined with screenshots and code, it handles product concepts, frontend designs, mockups, and game assets without leaving the app. If you build tools that combine AI agents with visual output, this integration shows how to collapse the design-to-code loop into a single workspace.
Plugin Ecosystem
OpenAI released more than 90 additional plugins that combine skills, app integrations, and MCP servers to give Codex more ways to gather context and take action. Notable additions include Atlassian Rovo for JIRA management, CircleCI, CodeRabbit, GitLab Issues, Microsoft Suite, Neon by Databricks, Remotion, Render, and Superpowers.
Automations and Memory
Codex automations now support reusing existing conversation threads, preserving previously built context. The tool can schedule future work for itself and wake up automatically to continue on a long-term task, potentially across days or weeks. Teams use automations for landing pull requests, following up on tasks, and tracking conversations across Slack, Gmail, and Notion.
A preview of memory allows Codex to retain useful context from previous sessions, including personal preferences, corrections, and information that took time to gather. Codex also proactively suggests useful work based on context from projects, connected plugins, and memory.
Developer Workflow Improvements
The update includes several workflow additions: support for addressing GitHub review comments directly, multiple terminal tabs, SSH connections to remote devboxes (in alpha), and a file sidebar with rich previews for PDFs, spreadsheets, slides, and docs. A new summary pane tracks agent plans, sources, and artifacts.
These updates are rolling out to Codex desktop app users signed in with ChatGPT. Personalization features including memory and context-aware suggestions will arrive later for Enterprise, Edu, EU, and UK users. Download the app to get started.
Get Insanely Good at AI
The book for developers who want to understand how AI actually works. LLMs, prompt engineering, RAG, AI agents, and production systems.
Keep Reading
Agent Skills vs Cursor Rules: When to Use Each
Cursor has both rules and skills for customizing the AI agent. They overlap, but they're not the same. Here's when to use each and how they interact.
How to Create Your First Agent Skill
A step-by-step guide to writing an agent skill from scratch: directory structure, SKILL.md format, effective descriptions, common patterns, and a complete working example.
What Are Agent Skills and Why They Matter
Agent skills are portable packages of instructions that extend AI coding agents. Here's what they are, how they work, and why the open standard changes how developers work with AI tools.
How to Use AI for Code Review
AI catches patterns, style issues, and common bugs fast. It misses business logic and architecture problems. Here's the practical workflow for using AI code review effectively.
Best AI Coding Assistants Compared (2026): Cursor vs Copilot vs Windsurf
A practical comparison of Cursor, GitHub Copilot, and Windsurf. Features, pricing, strengths, weaknesses, and which one fits your workflow in 2026.