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.
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:
- Open Settings → MCP and click Add Server.
- Pick the remote (HTTP) type and enter the URL
https://aicommander.dev/mcp. - Add the header
Authorization=Bearer <your-api-key>(Chatbox’s header field takesKEY=VALUElines), or see below for the no-account URL. - Check the connection, then save the server and make sure it is enabled.
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
- Long work: start detached jobs (
remote_job_start, thenremote_job_status/remote_job_logs) instead of one long tool call. - Models: pick a model with solid tool calling; the tools are the same whichever model you chat with.
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
- Remote shell on Linux, macOS, and Windows — by session code or saved alias.
- Detached jobs for builds, test suites, and training on the box that has the repo.
- Fleet list + GPU facts so your agent picks the right machine before it burns an hour.
- File courier (Pro) for checkpoints and diffs up to 100 MiB.
- Outbound-only agent on each machine — no inbound ports, no exposed SSH, no VPN to set up.
Not a replacement — a multiplier
| You already use | AI Commander adds |
|---|---|
| Chatbox | Settings → MCP → Add Server → https://aicommander.dev/mcp + API key header |
| Claude Code | claude mcp add --transport http … → remote exec + jobs |
| Codex / ChatGPT | Same MCP endpoint or REST /api/v1/exec |
FAQ
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.