Keep Devin.
Give it your machines.

AI Commander is not an alternative to Devin, Augment Code, Claude Code, Codex, ChatGPT, Cursor, GitHub Copilot, Sourcegraph Cody, Grok, Gemini, Windsurf, Continue, Cline, Roo Code, Zed, OpenCode, Qwen Code, goose, Amp, Kilo Code, OpenHands, or Amazon Q Developer. 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.

Quick start:
  1. Install the host agent on the machine you want your AI to control. It shows a private machine code.
  2. Connect your AI: paste this prompt, then replace AIC-… with your code — Help me connect this AI client to AI Commander using https://aicommander.dev/start.md. Then check the status of my machine: AIC-… — or add the connector URL https://aicommander.dev/mcp and sign in with an email code (per-client steps).
Positioning in one line: Devin stays the software engineer agent; AI Commander is the hands on the box — servers, GPU rigs, NAS, laptops — alongside Devin (including Outposts), not instead of it.

Sibling harness pages: Cursor · GitHub Copilot · Cody · OpenHands · Amazon Q · Augment · Aider · Cline · Roo Code · Zed · OpenCode · Qwen Code · goose · Amp · Kilo Code · Continue · Windsurf · Claude Code · Grok · Codex · ChatGPT · Gemini · Cua Spaces.

Connect Devin (MCP HTTP)

Devin by Cognition (custom MCP docs · CLI MCP config) supports custom remote MCP servers over HTTP (Streamable HTTP) in Cloud sessions and the Devin CLI. Point it at AI Commander’s hosted MCP endpoint:

Devin Cloud — custom HTTP MCP
Settings → Connections → MCP servers
→ Add a custom MCP
→ Transport: HTTP
→ Server URL: https://aicommander.dev/mcp

CLI / local config (~/.config/devin/mcp_config.json or .devin/mcp_config.json):

devin mcp add / mcp_config.json
$ devin mcp add aicommander https://aicommander.dev/mcp
{
  "mcpServers": {
    "aicommander": {
      "url": "https://aicommander.dev/mcp",
      "transport": "http"
    }
  }
}

Prefer a local stdio bridge? Add a STDIO custom MCP with command npx and args -y @aicommander/mcp (optional env AICOMMANDER_SERVER=https://aicommander.dev).

stdio bridge
$ npx -y @aicommander/mcp

Full client matrix (Devin, Augment, Claude Code, Codex, ChatGPT, Cursor, Copilot, Cody, Grok, Gemini, OpenCode, Qwen Code, goose, Amp, Kilo Code, Continue, Windsurf, Cline, Roo Code, Zed, OpenHands, Amazon Q, REST): Connect your AI client. Devin MCP docs: Using MCP with Devin · CLI MCP configuration.

First connect may open a one-time browser sign-in (OAuth Dynamic Client Registration). For a code-only first hour without that flow, append ?anonymous=1 to the MCP URL. For optional account features (saved aliases), pass a Bearer API key as an Auth Header where Devin supports it.

What you get that the session alone cannot

Devin remote control and AI Commander

Devin already has its own ways to work with your computer. The Devin CLI runs as a local agent in your terminal, and devin --cloud streams a Devin Cloud session into that terminal (Devin docs). Local Hands lets a cloud session you own run commands and edit files on the one machine where you run devin connect or approve the request in Devin Desktop, with your approval for each tool call by default (Devin docs; still rolling out). AI Commander works alongside these: Devin still decides what to do, and AI Commander gives it MCP tools to reach your other machines — servers, GPU rigs, NAS, Windows boxes — through a host agent that only connects outbound, with no SSH keys or open ports, plus detached jobs that keep running after the session ends.

Alongside Devin — not instead of it

Devin Outposts run Devin Cloud sessions with execution on infrastructure you operate. AI Commander does not replace Outposts or Devin Cloud. It is the shared MCP harness so Devin and your other coding tools can reach the same outbound-only fleet for shell, jobs, and files.

You already useAI Commander adds
DevinCustom HTTP MCP → https://aicommander.dev/mcp (or devin mcp add aicommander …)
Augment Codeauggie mcp add aicommander --transport http --url https://aicommander.dev/mcp
Amazon Q Developertype: http → https://aicommander.dev/mcp (or npx -y @aicommander/mcp)
OpenHandsopenhands mcp add aicommander --transport http https://aicommander.dev/mcp
Ampamp mcp add aicommander https://aicommander.dev/mcp
goosegoose session --with-streamable-http-extension "https://aicommander.dev/mcp"
Kilo Codemcp.aicommander.url → https://aicommander.dev/mcp
Claude Codeclaude mcp add --transport http … → remote exec + jobs
Codex / ChatGPTSame MCP endpoint or REST /api/v1/exec
Cursor / Continue / Windsurfnpx @aicommander/mcp stdio bridge
Copilot / CodyHTTP MCP / cody.mcpServers + bridge
Cline / Roo Code / ZedMCP settings / context_servers + bridge or remote URL

FAQ

Is AI Commander an alternative to Devin?
No. AI Commander is a remote-machine harness. You keep Devin (or Claude Code, Codex, ChatGPT, Cursor, GitHub Copilot, Sourcegraph Cody, Grok, Gemini, Windsurf, Continue, Cline, Roo Code, Zed, OpenCode, Qwen Code, goose, Amp, Kilo Code, OpenHands, Amazon Q Developer, Augment Code) as the AI. AI Commander gives those tools secure remote shell, detached jobs, and file transfer on machines you own — over MCP or REST. It is not a substitute for Devin Cloud sessions or Devin Outposts.
How do I connect Devin to AI Commander?
Add AI Commander as a custom remote MCP server in Devin. Cloud: Settings → Connections → MCP servers → Add a custom MCP → transport HTTP → URL https://aicommander.dev/mcp (optional Auth Header / OAuth). CLI: devin mcp add aicommander https://aicommander.dev/mcp (writes mcp_config.json). Prefer stdio? Point a STDIO custom MCP at npx -y @aicommander/mcp. First connect may open a one-time browser sign-in (OAuth). Use ?anonymous=1 for a code-only first hour. See /howto/ for the full matrix.
How is this different from Devin Outposts?
Devin Outposts run Devin Cloud sessions with execution on machines you operate — still Devin as the agent loop. AI Commander is a separate MCP harness: any MCP client (including Devin) can call remote shell, detached jobs, and file transfer on your fleet. Use them together when you want Devin plus shared machine access for other tools; do not treat AI Commander as an Outposts replacement.
Is AI Commander the same as Devin Local Hands?
No. Local Hands (devin connect or Devin Desktop) connects the computer you run it on to one Devin Cloud session you own, and by default you approve each tool call. AI Commander is a separate MCP server: Devin — and any other MCP client — can run shell commands, detached jobs, and file transfers on the machines you have enrolled, each running an outbound-only host agent. Use Local Hands for the computer in front of you and AI Commander for the rest of your fleet, or both together.
Can I use Devin remotely on my own servers?
Devin already has remote options of its own. devin --cloud runs a Devin Cloud session and streams it into your terminal, and Local Hands lets a cloud session you own run commands and edit files on one computer, and by default you approve each tool call (still rolling out). To give Devin shell commands and detached jobs on several of your own servers, GPU rigs or Windows boxes, add AI Commander as a custom HTTP MCP server (https://aicommander.dev/mcp) and enrol each machine with the outbound-only host agent. Devin stays the agent; AI Commander is the harness alongside it.

Next steps

Install the agent on a machine you control, connect Devin via custom HTTP MCP (or npx -y @aicommander/mcp), then ask for a real task on a remote box — alongside Devin, not instead of it.