OpenAI Codex 2026 Guide: AI Coding Agent, Models and Subscription Plans Explained

OpenAI's Codex began as a software development agent but now has more than 5 million weekly users. Non-developers—including analysts, marketers, designers and investors—account for about 20% of users and are growing more than three times as fast as developers. By packaging applications, skills and work instructions, plugins reflect Codex's shift from a coding tool to a platform for coordinating knowledge work.

OpenAI launched six role-based plugins on June 2, 2026, covering data analysis, creative production, sales, product design, public-equity investing and investment banking. Together, they integrate 62 applications and 110 skills, including Slack, Figma, Salesforce and Snowflake. The features are rolling out in supported regions, while Business and Enterprise administrators can manage application permissions.

OpenAI’s Codex is an AI agent that can write code, run tests and handle development tasks on a user’s behalf. Its expansion to the ChatGPT mobile app lets developers monitor work while away from their computers. GitHub’s Copilot App, meanwhile, strengthens parallel management of multiple agents and workflows, moving agentic development beyond the editor into a standalone desktop environment.

In July 2026, OpenAI began allowing users to connect remotely through the ChatGPT mobile app to Codex running on a Mac. Users can track progress, review output, approve actions and launch new tasks. During the same period, GitHub released a technical preview of the GitHub Copilot App, a desktop interface for centrally managing multiple workflows and agents. Neither company disclosed pricing or a date for full general availability.

OpenAI unveiled the agentic cybersecurity research tool under the codename Aardvark on October 30, 2025. It uses GPT-5 reasoning to analyze codebases, build threat models and validate vulnerabilities in a sandbox before Codex proposes fixes. Early testing identified 92% of known and synthetic vulnerabilities. The tool also uncovered 10 flaws in open-source projects that received CVE identifiers, highlighting AI's potential to shorten enterprise code security reviews.

On March 6, 2026, OpenAI formally renamed Aardvark Codex Security and released it in research preview. It is being rolled out gradually through Codex web to ChatGPT Pro, Enterprise, Business and Edu users, with the first month free. Tests on the same codebase showed alert noise fell by as much as 84%, the rate of severity overestimation dropped by more than 90%, and the overall false-positive rate declined by more than 50%.

OpenAI and Anthropic are competing for the AI software development tools market, with Codex going head-to-head with Claude Code. OpenAI President Greg Brockman has instructed engineering teams to make AI agents central to their daily development work. The aim is to shorten coding, testing and deployment cycles, deepen the model’s adoption in enterprise software workflows and strengthen the ChatGPT ecosystem.

OpenAI recently began a six-week product sprint that includes rapid releases of the Codex desktop app, GPT-5.4 and security-agent features. It also plans to combine ChatGPT, Codex and the Atlas browser into a desktop “super app.” The company has not disclosed the investment involved or exact release dates. The central goal of the update push is to counter Anthropic’s Claude Code.