Onepilot vs The Architect SSH

Your servers and your AI agents, in your pocket. Onepilot is the iOS app that runs your AI agents and server fleet on machines you own. Connect to any server, Mac, or VPS over SSH, then deploy, monitor, and manage agents across all of them from one place. Direct SSH to hardware you control: your keys and your code never touch the cloud. WHO IT IS FOR For developers, indie hackers, and sysadmins who run AI coding agents on remote machines and want to deploy, watch, and control them from a phone. PILLAR ONE: A REAL TERMINAL, PLUS THE TOOLS AROUND IT A full SSH terminal, not a chat box, with the modern dev workflow built in: browse and edit remote files, review git diffs, forward localhost to preview your dev server, and run terminal CLIs like Claude Code in a real session, exactly as you would on your laptop. Pair a server once with the onepilot CLI (one npm install and a QR scan) and your sessions become persistent: your shell keeps running on your own server through app closes and connection drops, and greets you with full scrollback when you return. SEE YOUR AGENTS THINK Onepilot detects the coding agent sessions running on your servers (Claude Code, Codex, OpenCode) and streams them live: follow every step as it happens, scroll the full transcript, then jump into the terminal to take over. PILLAR TWO: DEPLOY AND MANAGE AN AGENT FLEET Spin up a persistent AI agent in minutes with a guided wizard, no config files: pick a framework like OpenClaw or Hermes, choose a model, add your keys, connect a channel, and Onepilot keeps it running on your server. Watch every agent across every machine from a single view; swap the model, rotate a key, or adjust behavior anytime. KNOW WHEN SOMETHING BREAKS Fleet monitoring watches CPU, memory, disk, load, and your Docker containers on every paired host, learns each machine's normal, and sends a push notification when something drifts. Alerts are calm by design: one notification when a problem starts, spaced reminders while it lasts, and a recovery note when it heals. Drill into any container for live performance charts. RUNS WHILE YOU SLEEP Put any agent or task on a schedule with cron and let your fleet work overnight. This is automation no plain SSH client offers: your agents run even when your phone is asleep. SET UP ONCE, REUSE EVERYWHERE Store your keys and chat tokens one time, then reuse them across every agent. Give your agents new skills from a community marketplace. WHY ONEPILOT A plain SSH client connects you to a shell. Onepilot gives you that shell plus a full dev ecosystem around it, and an agent operations layer on top: deploy, monitor, alert, schedule, and manage a fleet of AI agents on your own servers. One app for every machine and every agent, not a remote control for one. Ships worldwide.

The models are good at typing. You are the one who knows what should be built. The Architect gives you one console for every harness you already run — attached over SSH, inside the screen and tmux sessions you already keep alive. No orchestration layer. No opinion about your workflow. Just direct hands on every agent you have running, from whichever device is in front of you. WHO IT IS FOR This is not an onboarding funnel with a terminal theme. It assumes you already run multiple harnesses and multiple models across real machines, and that your only missing piece is a decent way to reach them all from wherever you happen to be. It attaches to what you have already built and gets out of the way. Requires SSH, a session manager you already use (tmux or screen), and a harness — Claude Code, Codex, Aider, OpenCode, or the one you wrote yourself. A REAL TERMINAL Truecolor, correct UTF-8, live PTY resize, mouse reporting, and the Kitty keyboard protocol. On a touchscreen, swipe left or right to move between your screen and tmux windows. On desktop the same move is on buttons, so drag-to-select keeps working. EVERY SESSION AT A GLANCE One line per job: project, last output, elapsed time. When a session rings the terminal bell the badge lights and decays over sixty seconds — so you can tell an agent that wants you now from one that wanted you an hour ago, without opening anything. EXACT-NAME ATTACH screen and tmux matches session names by prefix, which is how people end up typing into the wrong agent. The Architect matches the name exactly and attaches by pid-qualified id, or creates fresh. It never guesses. THE SESSION OUTLIVES THE APP Sessions live on the remote host, not in the client. Close the app, lose signal, swap devices — the run keeps going and you reattach to it exactly where it is. SAME CONSOLE, EVERY SCREEN Not a stripped-down companion app on the phone and a real one on the desktop. The same terminal engine everywhere — the navigation adapts, the capability does not. CREDENTIALS STAY ON YOUR DEVICE SSH keys and passwords are held in the platform's secure storage, never in the app database and never on our servers. There is no account to create and nothing to sign in to. The app can generate a device identity keypair and install its public key on a host for you, so you can move off password auth without leaving the app. FREE AND PRO The free tier is one agent and one project, forever, with no account. Pro removes the limits — unlimited agents and projects — as a single one-time purchase. No subscription.