Bring your own subscription
T3 Code never resells tokens. It drives the agents you already pay for and are signed in to — no extra keys, no quota caps on top.
T3 Code is the open-source control plane for Claude Code, Codex, Cursor and friends. Run them in parallel, review the diffs, ship the PR — from your desk or your phone. Here’s everything you need to learn it.
npx t3@latestAddressStep, PaymentStep and a shared useCheckout hook. Editing 4 files…Diff · this turn
12- export function Form() { 12+ export function Checkout() { 13+ const s = useCheckout(); 14+ return s.step === 0 15+ ? <AddressStep {...s} /> 16+ : <PaymentStep {...s} />;
Terminals are great for one agent. They get messy at five. T3 Code runs a small server next to your repositories, starts the official agent harnesses for you, and streams everything to clean desktop, web and mobile clients.
State lives in SQLite on the server machine. Clients are thin views — they never run agents or Git themselves.
No home-grown agent loop. T3 Code talks to each provider’s own SDK or protocol, so behaviour matches the CLI.
Every agent’s output is normalised into one stream, which is why switching or mixing agents just works.
The pieces that make running several agents at once feel calm instead of chaotic.
T3 Code never resells tokens. It drives the agents you already pay for and are signed in to — no extra keys, no quota caps on top.
Switch models mid-conversation or hand a task from Claude Code to Codex without losing context or leaving the window.
One local server keeps every client in sync. Start a thread at your desk, approve the next step from your phone.
Give each thread its own Git worktree and branch, so parallel agents never trip over each other’s files.
Review diffs per turn, per branch or uncommitted — then commit, push and open a pull request with generated titles.
Performance is measured and dropped frames are treated as bugs. A GUI that keeps up with agents running in parallel.
Install an agent, sign in once on the server machine, and T3 Code picks it up. Your phone and browser never need the agent installed.
claude auth logincodex loginCursor SDKOpenCode SDKAgent Client ProtocolAgent Client Protocolits own CLI sign-inits own CLI sign-inits own CLI sign-inits own CLI sign-inAgent Client ProtocolPick your platform. Then install and sign in to at least one agent, like Claude Code or Codex.
brew install --cask t3-codecurl -fsSL https://t3.codes/install.sh | shwinget install T3Tools.T3Codescoop install extras/t3codeirm https://t3.codes/install.ps1 | iexyay -S t3code-binnix profile add github:NixOS/nixpkgs/nixos-unstable#t3codecurl -fsSL https://t3.codes/install.sh | shnpx t3@latestclaude auth loginDebian/Ubuntu: grab the .deb from the GitHub releases. Phone apps are on the App Store and Google Play.
Set it per thread. If a provider doesn’t support a mode, T3 Code falls back to asking.
First runs, unfamiliar repos, learning how an agent behaves.
Day-to-day coding where you still want to vet shell commands.
Trusted projects; routine actions flow, risky ones pause.
Sandboxed boxes and worktrees you can throw away. The default for new threads.
Plan mode is separate: it changes how the agent works (analyse first, then build), not what it’s allowed to touch.
Learn these and every screen in T3 Code makes sense.
Step-by-step walkthroughs we’re writing next. Each one tested on a real machine.
Install, sign in to an agent, open a project and ship a small change.
Coming soonSign-in, model picking and handing work between agents.
Coming soonPair your phone securely and approve steps from anywhere.
Coming soonRun several tasks at once without merge chaos.
Coming soonEvent sourcing, Effect RPC over WebSocket and provider adapters.
Coming soonWhen a control plane beats juggling CLI tabs — and when it doesn’t.
Coming soonT3 Code is a free, open-source (MIT) app for running coding agents such as Claude Code, Codex, Cursor and OpenCode from one interface. It runs a server on your machine and gives you desktop, web and mobile clients on top of it.
Neither. It is a control plane. The actual work is done by the agents you already have installed and signed in to; T3 Code manages their sessions, threads, Git workspaces and approvals.
Nothing. T3 Code is MIT licensed and has no paid tier. You only pay for whatever agent subscriptions you already use.
Claude Code, Codex, Cursor, OpenCode, Grok Build, Antigravity, Kiro, Pi, Muse Code, fx and any agent that speaks the Agent Client Protocol (ACP).
On macOS run “brew install --cask t3-code”, on Windows “winget install T3Tools.T3Code”, on Arch “yay -S t3code-bin”. To try it without installing anything, run “npx t3@latest”.
Yes. There are iOS and Android apps. Pair your phone with a one-time link or QR code over a trusted network such as your LAN, Tailscale or T3 Connect.
Project state stays on the machine running the server. Prompts, selected context and tool results still go to whichever agent provider you choose, exactly as they would without T3 Code.
Work stops, because the server and agents run on that machine. For unattended runs, use an always-on machine or a remote server.
Install T3 Code, connect the agents you already pay for, and run them side by side.