Skip to main content
Back to blog

OpenAI shipped a Codex macOS app: multi-agent threads + built-in git worktrees

OpenAI’s new Codex app for macOS is built for running multiple coding agents in parallel, with built-in git worktrees, skills, and automations. Here’s why that matters in real engineering workflows.

Damien GallagherFebruary 2, 20261 min read
aiopenaicodexdeveloper-toolsproductivity

OpenAI just released the Codex app for macOS. The interesting part isn’t “better autocomplete” — it’s workflow: you can run multiple agents in parallel, keep them separated by project/thread, and (critically) use Git worktrees so agents can work on the same repo without trampling each other.

Source: OpenAI announcement — Introducing the Codex app
https://openai.com/index/introducing-the-codex-app/

What the Codex app gives you (practically)

From OpenAI’s announcement, the Codex app includes:
  • Threads organised by project — each agent runs in its own thread, so context and diffs stay contained.
  • Built-in git worktrees — multiple agents can work on the same repo without branch/checkout chaos.
  • Diff review in the thread — review changes where the work happened; comment, iterate, then ship.
  • Skills — packaged workflows (instructions + scripts + resources) so agent work is repeatable.
  • Automations — scheduled runs for the boring-but-important stuff (CI babysitting, issue triage, release briefs), with results landing in a review queue.
It also carries over history/config from the Codex CLI and IDE extension, which is a nice touch if you’re already using it.

Why worktrees are the real feature

If you’ve tried running multiple agents against one repo, you’ve probably seen some mix of:
  • lockfile churn
  • accidental branch switching
  • partial changes overwriting each other
  • “it worked on the agent branch” but your local checkout is now inconsistent
Worktrees are the boring, correct solution. They make multi-agent work predictable: each agent gets an isolated working directory and branch, but the whole thing still feels like one repo.

How I’d actually use this

A realistic setup:
  • Agent A: fix CI failures / build issues
  • Agent B: implement a feature
  • Agent C: write tests + do a review pass
Each gets a worktree. You supervise diffs. You merge PRs. No heroics.

TL;DR

  • Codex app for macOS = multi-agent UI + project threads + built-in worktrees
  • Worktrees are the practical win: parallel agents without branch hell
  • Skills/Automations are promising, but the day-to-day value is isolation + review
If you’re building with agents today, this is one of the most “workflow-relevant” releases in a while.
Share this article