Save Your SSH Connections,
Run AI Agents on the Remote Box
AgentsRoom is an SSH connection manager and a built-in SSH terminal in one. Save your remote servers once, connect with an SSH key or a password, then run Claude Code, Codex or Antigravity CLI straight on the remote machine.
Stop juggling a separate SSH client and a code editor. Keep your connection profiles, your terminal and your AI coding agents in the same app, pointed at the same remote server.
How AgentsRoom connects to a saved SSH server and runs an AI coding agent straight on the remote machine.
Most AI coding agents assume your code lives on the same machine you are sitting at. But plenty of work happens on a remote server : a VPS, a staging box, a beefy build machine, a shared dev server the whole team uses. AgentsRoom treats that case as a first-class one. Save an SSH connection, open the built-in terminal over SSH, and you are working on the remote host as if it were local.
The SSH connection manager keeps a profile for every server you touch : host, port, user, and whether you authenticate with an SSH key or a password. No more digging through scattered config files or retyping the same long command. Pick a saved connection, hit connect, and the terminal lands you on the box in one step.
The payoff is running AI coding agents where the code actually is. Connect to your remote server over SSH, then launch Claude Code, Codex, Antigravity CLI or another agent on that machine. The agent reads and edits the files on the remote host, runs the test suite against the remote environment, and you drive the whole thing from AgentsRoom without a second SSH client open on the side.
An SSH Client Built for Running AI Agents
Connection management, a real terminal, and remote agent execution in one place.
Saved SSH Connections
Store a reusable profile for each remote server : host, port, user and auth method. Your VPS, your staging box and your team dev server all live in one list. Pick a connection and you are in, no command to retype.
Key or Password Auth
Authenticate with an SSH key or a password, whichever the server expects. Point a profile at your private key file or store a password, and AgentsRoom handles the handshake when you connect.
Built-in Terminal Over SSH
Every connection opens a real terminal on the remote host inside AgentsRoom. Full colored output, command history and copy-paste, served by the same terminal you already use for local projects. No separate SSH client to keep open.
Run Agents on the Remote Server
Launch Claude Code, Codex, Antigravity CLI or another agent directly on the remote machine over SSH. The agent works on the files that live on the server and runs commands in the remote environment, not on your laptop.
Attach SSH to a Project
Flag a project as remote and bind it to a saved SSH connection. From then on the project opens its terminals and agents on that server, so a remote codebase behaves like a normal AgentsRoom project.
Credentials Stay Local
Your SSH keys, passwords and connection details are stored on your own machine, never written into the project repo. Nothing about your servers leaks into a folder a teammate might clone.
Import Your ~/.ssh/config
The servers you already reach from a terminal come in as they are. AgentsRoom reads the host blocks in ~/.ssh/config, keeps the identity file each one declares, and preserves a ProxyJump through a bastion : it connects through the alias and lets OpenSSH resolve the block, exactly as your shell would.
AWS SSM Sessions
Reach an instance that has no public address and no inbound SSH port, through aws ssm start-session. The session is authorized by the AWS profile already configured on your machine, so there is no password and no key to store in the app.
Your Connection Details Never Leave Your Machine
An SSH connection manager is only useful if you can trust it with credentials. AgentsRoom keeps every SSH profile, key path and password in your local app data, not in the project you are working on. Connecting to a remote server never adds a config file to the repo and never commits a host or a secret by accident.
Authentication runs over standard SSH. Key-based login uses your existing private key, exactly as your shell would. Password login is sent over the encrypted SSH channel like any other SSH client. AgentsRoom is the client, your server stays the source of truth for what it accepts.
When you run an AI agent on the remote box, the code stays on the remote box. The agent reads and edits files on the server you connected to. Nothing about the remote project is copied to your laptop unless you ask for it, and your connection profiles are never shared with anyone else.
From Zero to Agent on a Remote Server
Save a connection once, run agents on it forever.
Save the SSH connection
Add a connection profile : host, port, user, and either your SSH key file or a password. Give it a name like prod-vps or staging and it is saved for next time.
Connect and open the terminal
Pick the saved connection and hit connect. AgentsRoom opens a built-in terminal over SSH on the remote host. You are now on the server, with full colored output and command history.
Run an AI agent on the box
Launch Claude Code, Codex or Antigravity CLI in that remote terminal. The agent works on the files on the server and runs against the remote environment, and you drive it from AgentsRoom like any other project.
When You Need Agents on a Remote Server
Not every codebase lives on your laptop.
Code on a VPS
Your app runs on a VPS and you want to fix it where it lives. Open the saved SSH connection, run a Claude Code agent on the box, and patch the bug against the real environment, dependencies and all.
Work on a staging box
A staging server reproduces a bug your laptop never will. SSH in, point a Codex agent at the staging codebase, and let it reproduce and fix the issue on the machine that actually shows it.
Shared dev server
The team works on one shared dev server. Everyone saves the same SSH connection, opens their own terminal, and runs their own agent on the host without setting up a local clone each.
No local setup needed
A heavy toolchain you do not want on your laptop lives on a build machine. Connect over SSH, run a Antigravity CLI agent there, and keep your own machine clean while the work happens remotely.
How can my AI agents access my SSH connections?
Through AgentsRoom MCP. Your saved connections are exposed to every agent as three MCP tools : ssh_list returns the servers usable in the current project, ssh_connect opens one of them as a real terminal tab, and ssh_connection_new proposes a server you have not saved yet. So when you tell an agent "connect to prod and read the logs", it does not have to guess a hostname or write an ssh command by hand : it reads your connection list and opens the right server.
Agent SSH access is deliberately credential-free. ssh_list only ever returns metadata: name, host, port, user, auth type and scope. Passwords and key passphrases stay encrypted in your OS keychain, private keys stay on your disk, and the desktop app injects the secret into the terminal itself. The agent names a connection, it never handles it.
Every session an agent opens is a visible terminal tab you can read, type into and close at any moment. Nothing runs on a remote machine behind your back, and a connection can be saved for a single project or globally, so an agent only ever sees the servers that make sense for what you are working on.
Proposing a connection is not creating one. ssh_connection_new opens the creation form pre-filled with what the agent found in a compose file, a deploy script or your documentation, and you are the one who reviews it, types the credential and saves. That limit is written into the tool rather than asked for in a prompt, because a connection an agent could register unseen would be a backdoor.
Discover AgentsRoom MCPFAQ
Can I save multiple SSH connections?
Yes. AgentsRoom works as an SSH connection manager : save a profile per remote server with its host, port, user and auth method, name them, and pick the one you need. Your VPS, staging box and shared dev server all live in the same list.
Does it support SSH key and password authentication?
Both. A connection can authenticate with an SSH key by pointing at your private key file, or with a password. AgentsRoom acts as a standard SSH client, so whichever method your server accepts is what you use.
Can I run Claude Code or Codex on a remote server through SSH?
Yes. That is the point of the feature. Open a saved SSH connection, then launch Claude Code, Codex, Antigravity CLI or another agent in the remote terminal. The agent runs on the remote machine and works on the files that live there, not on your laptop.
Where are my SSH credentials stored?
In your local app data on your own machine. Keys, passwords and connection details are never written into the project repo, so connecting to a server does not add config files or secrets to anything a teammate might clone.
Do I still need a separate SSH client?
No. AgentsRoom includes a built-in terminal over SSH, so your connection manager, your terminal and your AI agents are in one app. You can keep your usual SSH tools if you like, but you do not need a second client open just to reach the server.
Can my AI agents access my SSH connections?
Yes, through AgentsRoom MCP. Agents call ssh_list to see the servers saved for the current project (plus your global ones), then ssh_connect to open one as a terminal tab. It is the supported way for an AI agent to get SSH access: no hand-written ssh command, no credential pasted into a prompt.
Do my agents see my SSH password?
Never. The MCP tools only expose connection metadata (name, host, port, user, auth type). The password or key passphrase stays encrypted in your machine keychain and is injected into the terminal by AgentsRoom itself, after the agent has asked for the connection by its id.
Can I import my existing ~/.ssh/config?
Yes. AgentsRoom reads the host blocks in ~/.ssh/config and turns them into saved connections, keeping the identity file each block declares. Anything OpenSSH resolves on its own keeps working, a ProxyJump through a bastion included, because AgentsRoom connects through the alias and lets OpenSSH apply the block rather than trying to reimplement it.
Can I reach a server with no public address and no open SSH port?
Yes, with an AWS SSM connection. AgentsRoom opens the session with aws ssm start-session, authorized by the AWS profile already configured on your machine. There is no password and no key to store in the app, and the instance can stay closed to inbound SSH.
Can an agent create a new SSH connection?
It can propose one, never save one. ssh_connection_new opens the creation form pre-filled with the host, port and user the agent found in your deploy script or your documentation, and you review it, type the credential and save. Nothing is stored until you do, because a connection an agent could register without you seeing it would be a backdoor. When the host already exists in your ~/.ssh/config, importing it is the better route : it keeps the alias, so your bastions and your keys keep working.
You may also like
RDS through AWS SSM
Reach an Amazon RDS instance that has no public endpoint, from your own machine, through aws ssm start-session and the AWS-StartPortForwardingSessionToRemoteHost document. No bastion to maintain, no VPN, no inbound SSH rule. AgentsRoom opens the session on a loopback port and connects the SQL client through it. MySQL and MariaDB only, so RDS MySQL and Aurora MySQL-compatible.
Database Connections
Save your MySQL and MariaDB connections, reach a database in a private subnet through an SSH tunnel or an AWS SSM session, and let your AI agents query it over MCP. Read-only by default, one statement per call, capped result sets, and the password never reaches the agent.
Secret Manager
Store API keys, tokens and passwords in your OS keychain, reference them as {{secret:NAME}} in dev commands and agent environments, and let AgentsRoom resolve them at launch. Agents see the names, never the values, and nothing is ever synced to a server.
Repository import
Connect GitHub or GitLab, browse the repositories you actually have access to, and clone several at once. Each one becomes a project with its own AI coding agents. Self-hosted GitLab instances supported.
Dev Terminals
Per-project terminal manager and process launcher. Start backend, frontend and workers in one click, locally or on a remote server over SSH.
Remote Agent Control
Pilot your AI coding agents from your phone. Drive terminals, projects and prompts on your Mac or remote server from iOS and Android.
Localhost Tunnel (Live Preview)
Built-in secure tunnel that exposes a local or remote dev server as a public HTTPS URL. Preview your work in progress from anywhere.
Multi-Project, Multi-Agent
Run many projects and many AI agents in parallel, local and remote, from a single visual command center.
Bring Your AI Agents to the Remote Server
Download AgentsRoom, save your SSH connections, and run Claude Code, Codex or Antigravity CLI on any VPS or remote server through a built-in terminal.
Companion app: monitor your agents on the go
Bring your own: Claude, Codex, Antigravity CLI, or other AI provider.
Push bugs and requests straight to your public backlog.
A glimpse of AgentsRoom in action.