How I Use T3 Code To Work Across Claude, Codex, And Multiple Macs
AIThis post was created with the assistance of artificial intelligence (AI).

🔍 Read the full analysis: How I Use T3 Code To Work Across Claude, Codex, And Multiple Macs on ThorstenMeyerAI.com

Age 18–24?Offer from Amazon

Prime made for students and young adults

  • Fast, free delivery for dorm and study essentials
  • Prime Video and Amazon Music included
  • Member-only deals
Try Prime for Young Adults Free trial for eligible 18–24 year olds
As an affiliate, we earn on qualifying purchases.

TL;DR

Thorsten Meyer says he moved his AI coding workflow to T3 Code, connecting eight Macs and a Linux server to one workspace. He uses Claude Code to build and Codex to check changes, but reports no measured productivity gain and notes that some multi-machine features are still in beta.

Thorsten Meyer says he now manages Claude Code and Codex across eight Macs and a Linux server through one T3 Code workspace on his laptop. In a November 18 account on ThorstenMeyerAI.com, Meyer describes the change as a way to monitor parallel coding sessions and hand work between agents; he says he has not measured a productivity gain.

Meyer says his previous workflow split Claude Code and Codex across terminal windows, a terminal multiplexer and Claude’s desktop app, with separate sessions on each Mac. He used Claude Code to build and Codex to check changes. Tracking which machine needed attention, or transferring context from one agent to another, required him to move between tools and sessions.

He describes T3 Code as a shared interface for agents that users are already signed in to, rather than a service that resells their model usage. The project’s website calls it a “control plane for coding agents,” and Meyer says it is free and open source under the MIT license. Its documentation lists support for Claude Code, Codex and other coding agents. Users authenticate with the providers’ own logins, so provider plans and limits still apply.

In Meyer’s setup, a thread list brings sessions from connected machines into one view. He says that makes it easier to spot agents awaiting an answer and to pass a change from the agent that built it to one checking it. T3 Code also supports Git worktrees for separate threads, according to the article. The app’s documentation describes switching agents within a thread, but says the handoff does not carry over the previous agent’s reasoning, tool-call state or attachments.

At a glance
reportWhen: Described November 18, 2026; T3 Code ve…
The developmentThorsten Meyer has described moving his multi-agent coding workflow across eight Macs and a Linux server into one T3 Code workspace.

My switch to T3 Code · before and after

From terminal windows on many Macs to one workspace

The agents did not change. Claude Code and Codex still run on the Macs that do the work. What changed is where I see them: in one list of threads, on the laptop or the phone.

Before After Who did what? Who waits? Needs you Claude builds Codex checks Working Phone = remote
  1. 1 · BeforeSessions sit in terminal windows on each Mac. Nothing tells you which agent did what, or which one waits for you.
  2. 2 · One workspaceEach Mac runs T3 Code. One app connects to all of them, over the local network, Tailscale, SSH or T3 Connect.
  3. 3 · ThreadsOne thread per task. Claude Code builds, Codex checks. Busy threads fold away; a thread that needs an answer comes back to the top.
  4. 4 · RemoteThe phone approves the next step. The Mac keeps doing the work and has to stay on.

Sources: T3 Code README and user docs (remote access, working with threads, mobile notifications, FAQ), read November 18, 2026. Setup: the author’s own. Drawing: a generic interface, not a product screenshot.

Graphic: Powered by Thorsten Meyer AI

One View Across Coding Machines

The change speaks to a practical coordination problem for developers running several coding agents at once: the agents can work in parallel, but their sessions, approvals and changes may be scattered across machines. A shared interface could make it easier to see which task is running or waiting, and to route a change to another agent for review.

Remote access may also matter to people who cannot stay at their desks. T3 Code offers phone apps, and Meyer says a phone can alert users when an agent finishes, fails or needs input. The project’s FAQ says the phone acts as a remote; the computer running the agent must remain on. These are product capabilities described by Meyer and T3 Code, not independently measured results.

Meyer’s account is personal experience, not a controlled comparison. He explicitly says he has not measured whether the move made him more productive. The reported benefit is a consolidated view and a shorter path between building and checking—not a quantified improvement in output or speed.

DREAME D20 Air Plus Robot Vacuum and Mop with 20,000 Pa Suction

DREAME D20 Air Plus Robot Vacuum and Mop with 20,000 Pa Suction

Philips 5500 Series Fully Automatic Espresso Machine with LatteGo Milk System

Philips 5500 Series Fully Automatic Espresso Machine with LatteGo Milk System

De'Longhi Magnifica Start Automatic Espresso Machine with Milk Frother, Silver

De'Longhi Magnifica Start Automatic Espresso Machine with Milk Frother, Silver

As an affiliate, we earn on qualifying purchases.

From Terminal Sessions to T3 Code

Before switching, Meyer used Claude Code in terminals, a terminal multiplexer and the Claude Code desktop app. Codex ran in different terminal windows. He says each tool worked on its own, but he had to visit individual machines to check sessions and manually carry context between the agent that made a change and the one reviewing it.

T3 Code’s documentation describes several ways to connect machines, including a local network, Tailscale HTTPS, SSH and the project’s T3 Connect service. Meyer says T3 Connect is free for now and links up to three machines per account; he points to a paid plan for connecting more machines, as well as other connection methods. The project’s version was 0.1.10 on November 17, 2026, according to Meyer, who characterizes it as a young project changing quickly.

“I have not measured a productivity gain, so I won’t quote one.”

— Thorsten Meyer, writing on ThorstenMeyerAI.com

Beta Features and Practical Limits

Meyer’s account does not independently verify T3 Code’s performance, security or reliability across his machines. He says several multi-machine features remain in beta, including linked environments, through which agents on one machine can launch, message or stop threads on another. The extent to which these features work reliably across different networks and setups is not established in the article.

Access also has limits. T3 Connect is described as free “for now” and capped at three machines per account; other options include paid plans or alternative connection methods. The computer doing the work must stay on for remote control. Meyer also flags that new threads start in full-access mode, and users remain subject to the terms and usage limits of their own providers. The article does not give a detailed security assessment or report a measured productivity comparison.

What Users Should Check Before Switching

Meyer’s advice is conditional: the setup may suit people coordinating several agents, several machines or both, while a person who relies on one agent in one terminal may have little reason to switch. Potential users should check connection options, account limits, provider terms and the access level of new threads before linking machines.

The next test for T3 Code will be how its young, fast-changing project develops, particularly its beta features for machine-to-machine collaboration. Meyer has not announced a follow-up measurement or performance benchmark. For now, his report documents one multi-machine workflow and its perceived organizational benefits, while leaving the size of any productivity effect unquantified.

Key Questions

What is T3 Code?

It is an open-source app that provides a shared interface for coding agents users already access through their own provider accounts. Meyer says it does not resell tokens.

How is Meyer using it?

He says one workspace on his laptop connects eight Macs and a Linux server, with Claude Code and Codex on each Mac. He uses one agent to build and another to check changes.

Does Meyer report a productivity increase?

No. He says he has not measured a productivity gain. He reports a more centralized view of sessions and a simpler handoff between agents.

Can T3 Code control agents from a phone?

T3 Code’s documentation describes phone apps and remote alerts. The project says the computer running the coding agent must stay on; the phone does not do the coding work itself.

What limitations should users know about?

Meyer says some multi-machine features are in beta, T3 Connect is free for now with a three-machine account limit, and new threads start in full-access mode. Users must also follow their providers’ terms and plan limits.

Source: ThorstenMeyerAI.com

You May Also Like

A Skill Is a Folder, Not a Prompt: What Anthropic Learned Running Hundreds of Them

Anthropic reveals that organizing AI skills as folders containing instructions, scripts, and data improves consistency, onboarding, and scalability.

Could Your AI Agent Logs Reveal Hidden Reasoning?

Three October incidents point to risks in AI tool credentials and agent traces, though the scope and details of two cases remain limited.

Schema Harness Achieves ~99% On Arc‑AGI‑3 Public

Schema Harness achieves approximately 99% accuracy on Arc-AGI-3 public benchmark, marking a significant milestone in AI performance.

10 Best Home Theater Projectors Bringing AI Into Movie Nights In 2027

A projector roundup ranks Epson’s Home Cinema 2350 first, but its source names nine products and does not establish AI features or 2027 timing.