Editorial illustration for OpenAI updates Codex to run apps in background, targeting Anthropic's Claude Code
OpenAI Codex Now Runs Apps Autonomously in Background
OpenAI updates Codex to run apps in background, targeting Anthropic's Claude Code
OpenAI’s latest Codex upgrade arrives as the company squares off with Anthropic’s Claude Code, a move that signals a shift in how developers think about on‑device assistance. While earlier versions of Codex could generate code, the new release promises a more hands‑free experience, letting the model interact with local software without demanding the user’s constant attention. The update also claims the system can juggle several autonomous “agents” at once, a feature that could free programmers from toggling between windows or manually stitching together snippets.
Here’s the thing: OpenAI frames the change as a way to keep the assistant out of the way while you’re focused on other tasks, a subtle but potentially important distinction for anyone who’s tried to run AI‑driven tools alongside their regular workflow. The blog post that announced the change sums it up succinctly:
*Codex will now be able to operate desktop apps on your computer, OpenAI says in a blog post announcing the update. It can work in the background, meaning it won't interfere with your own work in other apps, and multiple agents can work in parallel. For developers, OpenAI says "this is helpful for te"*
Codex will now be able to operate desktop apps on your computer, OpenAI says in a blog post announcing the update. It can work in the background, meaning it won't interfere with your own work in other apps, and multiple agents can work in parallel. For developers, OpenAI says "this is helpful for testing and iterating on frontend changes, testing apps, or working in apps that don't expose an API." The feature will start rolling out to Codex desktop app users signed in with ChatGPT today and will initially be limited to macOS.
OpenAI did not indicate a timeline for when use will expand to other operating systems. EU users will also have to wait, it said, adding that the update will roll out to users there "soon." Codex is also getting the ability to generate and iterate on images with gpt-image-1.5, new plugins for tools like GitLab, Atlassian Rovo, and Microsoft Suite, and native web browsing through an in-app browser, "where you can comment directly on pages to provide precise instructions to the agent." OpenAI also said it will also be easier to automate tasks, with users able to re-use existing conversation threads and Codex now able to schedule future work for itself and wake up automatically to continue on a long-term task.
Can it really stay invisible? OpenAI’s latest Codex update pushes the system into a more agentic role, letting it launch and control macOS applications without user prompting. It runs quietly.
The blog post stresses that the AI can run in the background, so it won’t clash with a user’s active windows, and that several agents may operate simultaneously. Image generation and experience‑based memory are also added, expanding the tool beyond pure code synthesis. OpenAI frames the changes as a direct response to Anthropic’s Claude Code, positioning the two as rivals in the emerging developer‑assistant market.
Yet the practical benefits remain to be proven; developers have yet to see how background operation impacts system resources or workflow stability. The announcement hints at “helpful” outcomes for programmers, but concrete use‑case examples are absent. Whether the parallel‑agent architecture will scale reliably on typical hardware is still unclear.
In short, the upgrade broadens Codex’s functional scope, but its real‑world effectiveness is an open question.
Further Reading
- Introducing the Codex app - OpenAI
- What Is the OpenAI Codex Plugin for Claude Code? Cross-Provider ... - MindStudio
- Codex vs Claude Code: which is the better AI coding agent? - Builder.io
- Introducing Codex Plugin for Claude Code - OpenAI Community
Related Reading
Browse all OpenAI news →
LLMs & Generative AI Ant Group unveils Ring-1T, first open-source trillion-parameter reasoning model
LLMs & Generative AI ChatGPT Health Event Shows AI Modernizing Dev Workflows, GitLab Unveils Plans
LLMs & Generative AI Gen AI app sessions up fivefold, downloads jump 778% as ChatGPT leads traffic
Related Topic OpenAI, a Series F San Francisco startup founded in 2015 by eight pioneers
Business & Startups
Related Topic GPT-5 helps mathematicians offload tedious tasks, says Timothy Gowers
Open Source
From Archives Gemini app uses Google Photos to generate personalized images
From Archives Anthropic releases Claude Opus 4.7, launches Cyber Verification Program for pros
From Archives Implementing Context-Aware Long-Term Memory for AI Agents via Mem0 and OpenAI
From Archives OpenAI launches GPT-5.4-Cyber, a defensive cybersecurity model for vetted pros
Common Questions Answered
How does OpenAI's latest Codex update change background application interactions?
The new Codex version can now operate desktop apps autonomously in the background without interrupting user workflows. This allows multiple AI agents to work simultaneously on different tasks, providing developers with more flexible testing and interaction capabilities.
What specific advantages does the Codex update offer for developers?
OpenAI's update enables developers to use Codex for testing frontend changes, running app tests, and working within applications that lack exposed APIs. The background operation mode allows for more seamless and unobtrusive software development and interaction processes.
How does the new Codex version compare to previous iterations in terms of functionality?
Unlike earlier versions that primarily generated code, the updated Codex can now interact with local software autonomously and run multiple agents in parallel. The system has expanded beyond pure code synthesis to include features like background app control and potential image generation capabilities.