AIThis post was created with the assistance of artificial intelligence (AI).

TL;DR

Thorsten Meyer says he moved Claude Code and Codex sessions across eight Macs and a Linux server into one T3 Code workspace. He describes easier session tracking and handoffs, but has not measured a productivity gain; several multi-machine features remain in beta.

Developer Thorsten Meyer says he now manages Claude Code and Codex sessions across eight Macs and a Linux server through one T3 Code workspace on his laptop. His account describes a change in how he monitors and hands off coding tasks across machines, though he reports no measured productivity gain and notes that several multi-machine features are still in beta.

Buying for a business?Offer from Amazon

Get business pricing on tech for your team

  • Business-only prices and quantity discounts
  • Tax-exempt purchasing
  • Multiple users, one account, clear invoices
As an affiliate, we earn on qualifying purchases.

Meyer says the coding agents still run on the computers doing the work. T3 Code provides a shared view of their sessions, which it organizes as threads. Before switching, he used terminal windows, a terminal multiplexer and Claude Code’s desktop app, while Codex sessions ran in separate terminals. Each Mac had its own sessions, requiring him to check machines individually to see what was running or waiting for input.

In his new setup, Meyer uses one agent to build and another to check changes. He says the shared thread list makes it easier to see which agent is working and which needs a response. The project’s documentation describes ways to connect machines, including a local network, Tailscale, SSH and T3 Connect. Meyer also says he can use a phone to respond remotely while the Mac running the task stays on.

T3 Code is described by its makers as a free, open-source app that controls coding agents users are already signed in to; it does not resell their tokens, according to Meyer. Its documentation says T3 Connect is free “for now” and supports up to three machines per account. The article says other connection methods are available, and that a paid T3 Chat plan supports more machines. Provider subscriptions, terms and plan limits still apply.

At a glance
reportWhen: Published November 18, 2026; the cited…
The developmentThorsten Meyer reported on November 18, 2026, that he had moved his multi-machine Claude Code and Codex setup into a shared T3 Code workspace.
Board titled Three reasons, and what T3 Code offers for each. One: several Macs, one surface; agents keep running where they are, one app connects over the local network, Tailscale, SSH or T3 Connect, and iOS and Android apps act as remotes. Two: Claude and Codex in one place; switch models mid-thread, let Claude hand a task to Codex, or start a second agent in the same worktree to check the change. Three: many agents at a glance; one thread per task, an Agents view for subagents, and a Working section that sends a thread back to the top when it needs you. Highlighted note: no tokens resold; T3 Code drives the agents you are already signed in to, and your plans, terms and limits stay as they are
My three reasons for switching, and the matching T3 Code features. Sources: t3.codes and the T3 Code README and user docs on GitHub, read November 18, 2026. Board: Thorsten Meyer AI.

Following Agents Across Machines

Meyer’s report speaks to a practical coordination problem for developers running several AI coding sessions at once: the work can be spread across machines while oversight remains fragmented. A shared thread list can make it easier to spot tasks awaiting approval and pass work from an implementation agent to a reviewing agent, based on his experience.

That account is a description of one user’s workflow, not evidence of a general productivity improvement. Meyer explicitly says he has not measured a productivity gain. For teams considering a similar setup, the relevant question is whether bringing sessions into one interface reduces the effort of tracking work enough to justify adopting a young, fast-changing tool.

Products Worth Considering

Kindle Paperwhite Signature Edition 32GB (2024 Model) - Metallic Black

Kindle Paperwhite Signature Edition 32GB (2024 Model) – Metallic Black

Apple AirPods Pro 3 Wireless Earbuds with Active Noise Cancellation

Apple AirPods Pro 3 Wireless Earbuds with Active Noise Cancellation

As an affiliate, we earn on qualifying purchases.

From Terminals to Shared Threads

Meyer says he runs multiple AI coding agents in parallel, with one tool building and another checking changes. Previously, Claude Code and Codex sessions lived in separate terminal windows on different Macs. That arrangement worked, he writes, but made it harder to tell which agent had touched a file or was waiting for approval.

The article refers readers to an earlier T3 Code feature tour and focuses on Meyer’s reasons for switching and his current setup. It cites the project’s README and user documentation, read on November 18, 2026, and identifies version 0.1.10 as released November 17. These details describe the project at that time and may change as it develops.

“T3 Code runs the coding agents on your machine and gives them one fast interface. Start a thread at your desk, then approve the next step from your phone.”

— T3 Code documentation, as quoted by Thorsten Meyer

Beta Features and Open Questions

Meyer says several multi-machine features remain in beta, and describes T3 Code as a young project that moves quickly. The source does not specify which parts of his eight-Mac and Linux setup depend on beta features, or how reliably the arrangement performs across different networks and devices.

The article provides no measured comparison of task completion time, error rates or productivity before and after the switch. It also does not establish whether the current T3 Connect terms will continue, or how future changes might affect machine limits. Users remain subject to the terms and usage limits of their AI providers.

How the Setup Develops

Meyer says additional machines can join the workspace, and he expects to keep using the setup to coordinate parallel coding sessions. T3 Code’s version and beta features may change as the project develops; the article does not give a timetable for updates or for beta features to become stable.

Readers evaluating the tool can compare its connection options and machine limits with their own workflow, then check the current documentation and provider terms. Meyer’s account suggests the setup is most relevant to people who already manage several agents or machines; he says a single agent in one terminal may not call for a change.

Key Questions

What changed in Meyer’s workflow?

He moved from separate terminal sessions on multiple Macs to a shared T3 Code workspace that lists agent sessions as threads.

Do the AI agents run in T3 Code?

According to Meyer’s description of the product, the agents continue running on the user’s machines. T3 Code provides an interface for managing their sessions.

Does Meyer say T3 Code made him more productive?

No quantified gain is reported. Meyer says he has not measured productivity; he describes improvements in tracking and coordinating sessions.

What should users check before adopting it?

Check the current connection options, machine limits and beta status. The article says provider terms and plan limits still apply, and T3 Connect was described as free “for now.”

Source: Thorsten Meyer AI

You May Also Like

Need AI Credits For Your Startup? Explore SpaceXAI’s Grok Program

xAI says approved startups can use shared credits across four Grok products and receive hands-on support, but key program terms are not yet public.

AI Automation Software Deals: A Black Friday Guide

Compare AI automation software deals by total cost, integrations, contract terms, and real workflow results before you sign.

Could ChatGPT Ads’ Expansion In Southeast Asia And Taiwan Reshape AI Advertising?

OpenAI says ChatGPT Ads is expanding to Southeast Asia and Taiwan, adding new markets while leaving launch details, pricing and ad formats unclear.

A $1,279 Exploit, Faster Labs, And The Signals In GPT-6 Cyber

OpenAI says GPT-6 Cyber produced 948 Linux privilege-escalation exploits. METR separately reports faster AI progress at Anthropic, with much evidence withheld.