Keep Chatbox.
Give your models your machines.

AI Commander is not an alternative to Chatbox, Claude Code, Codex, ChatGPT, or any other AI client. It is the remote-machine harness those tools plug into over MCP: outbound-only shell, detached jobs that outlive the chat, and file transfer on hardware you already own.

Positioning in one line: Chatbox stays your desktop AI chat across models; AI Commander is the hands on the box — servers, GPU rigs, NAS, laptops — with no inbound ports and no exposed SSH.

Sibling harness pages: Msty Studio · Jan · LM Studio · AnythingLLM · TypingMind · Open WebUI · Claude Code · Codex · Claude Desktop — and the rest on Connect your AI client.

Connect Chatbox (Settings → MCP, remote server)

Chatbox supports MCP since version 1.14 (Chatbox docs: MCP). Add AI Commander’s hosted endpoint as a custom remote server:

  1. Open Settings → MCP and click Add Server.
  2. Pick the remote (HTTP) type and enter the URL https://aicommander.dev/mcp.
  3. Add the header Authorization=Bearer <your-api-key> (Chatbox’s header field takes KEY=VALUE lines), or see below for the no-account URL.
  4. Check the connection, then save the server and make sure it is enabled.
Chatbox → Settings → MCP → Add Server
Name:    aicommander
URL:     https://aicommander.dev/mcp
Header:  Authorization=Bearer <your-api-key>

Or try it without an account through Chatbox’s one-click install link, which opens Chatbox with the anonymous URL https://aicommander.dev/mcp?anonymous=1 pre-filled (code-only first hour): Add AI Commander to Chatbox.

Create an API key in the AI Commander dashboard (see Accounts & API keys) and send it as the Authorization: Bearer header so the agent can list your machines and reach them by alias. No account yet? Use https://aicommander.dev/mcp?anonymous=1 as the URL instead (no header) for a code-only first hour, reaching machines by their AIC-… session code.

Get the details right

By default, API keys and OAuth connectors only act while the account owner has opened the AI Commander dashboard in the last 24 hours (accounts can disable that gate under Credential security) — see Connect your AI client. AI Commander’s endpoint is first-party and only acts on machines where you installed the agent yourself. Menus and options can differ between Chatbox versions — check the linked Chatbox docs for your build.

What you get that the chat alone cannot

Not a replacement — a multiplier

You already useAI Commander adds
ChatboxSettings → MCP → Add Server → https://aicommander.dev/mcp + API key header
Claude Codeclaude mcp add --transport http … → remote exec + jobs
Codex / ChatGPTSame MCP endpoint or REST /api/v1/exec

FAQ

Is AI Commander an alternative to Chatbox?
No. AI Commander is NOT an alternative to Chatbox. It is a remote-machine harness. You keep Chatbox and your models (or Claude Code, Codex, ChatGPT, Cursor, and the other clients on /howto/) as your AI front end. AI Commander gives those tools secure remote shell, detached jobs, and file transfer on machines you own — over MCP or REST. It is also not an alternative to Claude Code, Codex, or ChatGPT; it works with them the same way.
How do I connect Chatbox to AI Commander?
Open Settings → MCP, click Add Server, choose the remote (HTTP) type, enter https://aicommander.dev/mcp, add an Authorization: Bearer API key header (or use https://aicommander.dev/mcp?anonymous=1 without a header for a code-only first hour), check the connection and save. Chatbox 1.14 or later is required.
Is there a one-click install for Chatbox?
Yes. Chatbox handles chatbox://mcp/install links with a base64-encoded server config; the link on this page pre-fills AI Commander's anonymous URL (https://aicommander.dev/mcp?anonymous=1) so you can try it without an account and add your API key later.

Next steps

Install the agent on a machine you control, add AI Commander in Chatbox under Settings → MCP (https://aicommander.dev/mcp), then ask your model for a real task on a remote box.