Use a Codex CLI account or ChatGPT subscription sharing to code in T3 Code.
Choose Settings > Providers > Inference accounts to sign in on one host and run Codex threads on environments paired over Tailscale or your trusted LAN. Each thread keeps its workspace and tools on the environment where it runs. Host and share inference accounts
Connect during onboarding or in Settings → Providers. For a remote machine, select that environment first. T3 Code handles Codex installation; sign in on OpenAI and allow sharing of your ChatGPT plan.
Manage shared usage and credits in ChatGPT through Manage usage in T3 Code. If a request uses a feature that ChatGPT sharing does not support, use another provider for that request.
Fast and Ultrafast speeds are unavailable with this connection. To use the speed options your account supports, use an existing Codex login.
When reconnecting, choose the same account in T3 Code and on OpenAI's sign-in page. Disconnecting stops running threads but keeps their history and lets you reconnect later.
If remote sign-in cannot return automatically, paste the full URL from the final localhost page into the sign-in panel, even if that page could not load.
Choose Use existing Codex CLI when adding the provider to use the CLI's current
login and settings. Run codex login on the environment's machine to sign in.
Provider setup covers installation and custom configuration.
Run traex-bridge at 127.0.0.1:8317 on the selected environment's macOS or Linux
machine. Store its API key in ~/.traex-bridge/api-key on that machine.
In Settings > Providers, choose Add provider, then Traex.
The preset uses Codex from that machine's PATH or a copy T3 Code has installed.
To use another executable, set its path in Config.
Traex stores its sessions and configuration in a separate Codex home.
Add accounts on the inference host, then turn on Use CLI proxy for Codex on each environment that needs them. Threads keep using the normal Codex provider and model names. While the proxy is on, other Codex accounts on that environment are hidden; turn it off to use an individual CLI login again. Host and share inference accounts
Codex can ask a question and keep working. Answer it in the thread's question panel. The answer becomes a new message: it reaches the active turn, or starts another turn if Codex has finished. Unanswered questions survive reconnects. If you do not want to answer, dismiss the question from its panel. Dismissing closes it without sending anything to Codex. This requires a Codex version that supports async questions.
If your Codex instance already has native Computer Use configured and enabled, ask it to work in a Mac app, such as Calculator. Computer Use controls the server environment's Mac, even when you connect from another computer or your phone. Native permissions and confirmation requests still apply.
Codex tools can request access to another app. Respond to the named app's request in the thread on web, desktop, or mobile. Some tools offer access for one request, the current session, or permanently. See Permission modes for command and file approvals.
When Codex stops on a usage limit, the thread names the window that ran out and when it resets, when Codex reports them. Send the message again after the reset. On a workspace plan the message also says whether your workspace owner needs to add credits or raise the spend limit to continue sooner.
In an existing Codex thread, send /feedback with an optional description, for
example /feedback The agent stopped before finishing the tests. This uploads
the conversation and Codex logs to OpenAI. The returned thread ID can be shared
with OpenAI support.