T3 Code: A Free, Open-Source Control Panel for Claude Code, Codex and Other Coding Agents Theo Browne's team released T3 Code, a free, MIT-licensed open-source control panel that runs Claude Code, Codex, Cursor CLI, OpenCode and other coding agents side by side from a single server. The server owns agent processes, terminals, Git operations and project files, while desktop, web and mobile apps act as thin clients, with per-thread branches or worktrees, in-app diff review and PR creation, remote control, and an MCP server that lets other agents read and start threads. It drives the official CLIs and signs in through each provider's own login, so users keep paying only their existing Anthropic, OpenAI or Cursor costs. If you use AI coding agents every day, you have probably hit this wall: three terminals running Claude Code, one running Codex, all poking at the same repo, and no single place to see what each one is doing or what it changed. T3 Code is an attempt to fix that. It comes from Theo Browne's team the people behind the T3 Stack and T3 Chat , it is MIT licensed, and it costs nothing. In this post I will cover what it actually is, how to get it running, what you need to watch out for, and how it stacks up against the free and paid alternatives. The project describes itself as an "agent harness control surface". In plain terms: You desktop / web / phone | v T3 Code server <-- owns processes, terminals, Git, project files | +------+-------+-----------+----------+ | | | | | Claude Codex Cursor CLI OpenCode Grok / Antigravity Code CLI A server process on your machine owns everything that runs: the agent processes, terminals, Git operations and project files. The desktop, web and mobile apps are thin clients that connect to that server. The desktop app bundles its own server, so on a single machine you do not have to think about this split at all. Because T3 Code drives the official CLIs, it signs in through each CLI's own login. It does not resell API keys or add its own usage quota. Whatever you pay Anthropic, OpenAI or Cursor today is what you keep paying. T3 Code itself is $0. One window for many agents. Run Claude Code and Codex side by side, compare their approaches on the same problem, and switch models in the middle of a thread. Branch per thread. Each thread can work on its own branch or Git worktree. A worktree is a second checkout of the same repo on a different branch, so two agents can edit files at the same time without stepping on each other. Diff review and PRs in the same place. You see the diff as the agent works, then commit, push and open a pull request from the app. The PR gets a generated title and body. Remote control. Leave the agents running on your workstation and check on them from your phone or laptop. An MCP server. Other agents Claude Code in a terminal, Codex, ChatGPT can connect to T3 Code over MCP to read threads and start new ones. That makes a "coordinator agent" pattern possible without writing your own plumbing. T3 Code cannot do anything without an agent behind it. Set up at least one of these first: Claude Code claude auth login Codex codex login Cursor CLI agent login OpenCode opencode auth login Grok Build grok login Google Antigravity is the exception: you enable it inside T3 Code's settings and sign in with Google. No CLI needed. Pick whichever fits your workflow. Try it once without installing anything permanent: npx t3@latest Install the CLI server plus local web app : macOS / Linux curl -fsSL https://t3.codes/install.sh | sh Windows PowerShell irm https://t3.codes/install.ps1 | iex Then: t3 start the server and open the local web app t3 service install keep it running in the background t3 update move to a newer release t3 --help full reference Install the desktop app: macOS brew install --cask t3-code Windows winget install T3Tools.T3Code or scoop install extras/t3code Debian / Ubuntu download the .deb from GitHub Releases first sudo apt install ./T3-Code- .deb Arch Linux yay -S t3code-bin Do this before your first real task. See the next section for why. Add your repo as a project, start a thread, choose the agent and whether it should run in a new worktree, and give it a task. When it finishes, review the diff and decide whether to open a PR or throw the branch away. Every thread has a permission mode that decides how much the agent can do without asking you: | Mode | What it does | When to use it | |---|---|---| | Supervised | Asks before commands and file changes. Work outside the workspace is restricted. | Important repos, unfamiliar tasks | | Auto-accept edits | File edits go through, commands still need approval | Refactors where you mainly care about shell commands | | Auto | Routine actions run, risky ones still ask | Day-to-day work with providers that support it | | Full access | No prompts at all for commands or edits | Throwaway worktrees and sandboxes only | Two things to know: The mode is set per thread, so changing it in one thread does not affect others. The machine running T3 Code does the work. Your phone or laptop is just a remote. That means the host has to stay awake and reachable. You have three main ways to connect: LAN or Tailscale traffic stays on your network : t3 serve --host