Codex Desktop App + Free GPT-5.2 Codex (Tested): Is OpenAI Now Copying Conductor,Commander?

Why It Matters

A subpar developer UI could slow OpenAI’s push to make Codex a mainstream coding assistant, giving rivals like Verdant a competitive edge in the emerging AI‑code tooling market.

Key Takeaways

• OpenAI releases native macOS Codex desktop app, free for a month.
• UI mimics Conductor, but suffers from bugs and design flaws.
• Only GPT‑5.2 medium model selectable; other models unresponsive.
• Skill installation limited; custom skills require manual config edits.
• App’s sandboxed execution and diff view useful despite performance issues.

Summary

OpenAI has introduced a native macOS Codex desktop application, offering a graphical interface for its code‑generation model and a free‑plan trial lasting one month. The app replaces the earlier terminal‑only and VS Code extension experiences, promising faster, native performance on Apple hardware.

The interface closely mirrors the design of Conductor, featuring threads, work‑tree‑style project organization, a skills tab, and automation scheduling. However, the reviewer notes several functional shortcomings: only the GPT‑5.2 medium model can be selected, custom skill installation requires manual edits to the config folder, and the UI exhibits padding and rendering glitches.

During testing, the app failed to inherit file context, displayed erratic behavior when switching tabs, and opened multiple VS Code windows when editing files—issues the reviewer describes as “vibecoded” for a trillion‑dollar company. Positive aspects include a sandboxed command runner and a clear diff viewer, which the reviewer compares favorably to Verdant’s more polished agentic UI.

These shortcomings suggest OpenAI’s first foray into a full‑featured developer IDE may lag behind specialized competitors, potentially limiting adoption among power users who demand reliable automation and seamless integration. The app’s mixed reception underscores the importance of UI polish and extensibility in AI‑assisted development tools.

Original Description

In this video, I take a deep dive into the newly launched OpenAI Codex App for macOS. I explore its transition from a terminal/VS Code extension to a graphical interface, testing its capabilities in automation, skills, and project management while highlighting some baffling design choices and bugs.

--

Key Takeaways:

🖥️ OpenAI’s new Codex App offers a native-feeling macOS interface with background task capabilities.

🆓 Free plan users get one month of access, while subscribers enjoy 2x rate limits.

🤖 The app introduces "Skills" and "Automations" allowing for scheduled tasks and self-running agents.

🐛 The UI feels "vibecoded" with significant padding issues and visual glitches in the Skills tab.

🔒 Currently, model selection appears bugged, locking users to GPT-5.2 Codex Medium.

📉 Context awareness is inconsistent, sometimes requiring config deletions to read files properly.

🆚 The agentic UI falls short compared to competitors like Verdent, particularly in memory management and workflow.