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.
- Install the host agent on the machine you want your AI to control. It shows a private machine code.
- 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 URLhttps://aicommander.dev/mcpand sign in with an email code (per-client steps).
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:
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):
{
"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).
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
- Remote shell on Linux, macOS, and Windows — by session code or saved alias.
- Detached jobs for builds, training, and headless agents on the box that has the repo.
- Fleet list + GPU facts so Devin (or any sibling client) picks the right machine before it burns an hour.
- File courier (Pro) for checkpoints and diffs up to 100 MiB.
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 use | AI Commander adds |
|---|---|
| Devin | Custom HTTP MCP → https://aicommander.dev/mcp (or devin mcp add aicommander …) |
| Augment Code | auggie mcp add aicommander --transport http --url https://aicommander.dev/mcp |
| Amazon Q Developer | type: http → https://aicommander.dev/mcp (or npx -y @aicommander/mcp) |
| OpenHands | openhands mcp add aicommander --transport http https://aicommander.dev/mcp |
| Amp | amp mcp add aicommander https://aicommander.dev/mcp |
| goose | goose session --with-streamable-http-extension "https://aicommander.dev/mcp" |
| Kilo Code | mcp.aicommander.url → https://aicommander.dev/mcp |
| Claude Code | claude mcp add --transport http … → remote exec + jobs |
| Codex / ChatGPT | Same MCP endpoint or REST /api/v1/exec |
| Cursor / Continue / Windsurf | npx @aicommander/mcp stdio bridge |
| Copilot / Cody | HTTP MCP / cody.mcpServers + bridge |
| Cline / Roo Code / Zed | MCP settings / context_servers + bridge or remote URL |
FAQ
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.