DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to run a Codex agent next to your Claude Code agents with Chums

Switch one character from Claude Code to Codex and follow its terminal on the Mac.

Who it is forA developer who uses both Claude Code and Codex and wants to pick the right agent per task from the same watch.

The problemEach coding agent usually lives in its own terminal, so you cannot manage them together from one place.

The outcomeEach agent is its own session and character, you can switch between them on the watch, and a Codex agent can be followed and typed into on the Mac.

What you need first

  • A Mac with Apple silicon on macOS 15.6 or later, with Xcode 26 and XcodeGen
  • An Apple Watch on watchOS 26 paired with an iPhone on iOS 26, and a USB cable for the iPhone the first time
  • Node.js 20.11 or later
  • Claude Code and/or Codex CLI, signed in
  • WhisperKit CLI and ffmpeg
  • A free Tailscale account for Funnel
  • An Apple ID in Xcode (a free Personal Team works)

Steps

  1. Install Codex CLI and sign it in, then complete the main setup with bin/chums-setup
  2. On the watch, swipe the agent's row left in the agents list and choose Runs on, then pick Codex
  3. Open a Codex terminal on the same conversation: bin/chums-codex
  4. Tap the faces at the top left of the watch to switch agents before you speak
  5. Check the whole chain after switching: bin/chums-doctor

Prompt for your agent

In the chums repo at <target-folder>, run bin/chums-codex and confirm a Codex terminal opens on the same conversation as the watch agent. Expected output: a Codex session you can follow on the Mac. Verify with bin/chums-doctor that the Codex path reports no failures.

Caveat. The README describes Codex agents as run by the hub through Codex's app-server protocol, and other agents such as Copilot are experimental.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page