Onepilot vs MLX Companion

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.

MLX Companion è il client iOS per MLX Studio sul tuo Mac. L’app non esegue modelli AI sul telefono: chat, agente, generazione immagini/video e collaborazione avvengono sul tuo Mac Apple Silicon, mentre iPhone e iPad fungono da telecomando mobile con interfaccia ottimizzata. COSA PUOI FARE • Chat con i modelli MLX caricati sul Mac • Agente remoto e cronologia sessioni sincronizzata con il browser Mac • Monitor operazioni (training, generazione, job in corso) • Galleria media generata sul Mac • Hub team / collaborazione quando abilitato su MLX Studio • Widget home screen con stato Mac (RAM, job, connessione) COME FUNZIONA 1. Installa e avvia MLX Studio sul tuo Mac (Apple Silicon). 2. Abilita MLX Link nella tab Link di MLX Studio. 3. Apri MLX Companion su iPhone e completa il pairing (QR sulla stessa rete o relay MLX Link). 4. Usa l’app ovunque: a casa via LAN veloce, fuori casa via relay MLX Link (HTTPS). REQUISITI • Mac con MLX Studio installato e in esecuzione • Account Apple per TestFlight/App Store (nessun account MLX obbligatorio) • Pairing iniziale con il tuo Mac PRIVACY I prompt e i file restano sul tuo Mac. L’app conserva solo il token di pairing nel Keychain iOS. Nessun servizio cloud MLX per l’inferenza. MLX Companion è software companion open source per utenti di MLX Studio. Non è un chatbot cloud indipendente. MLX Companion is the iOS client for MLX Studio on your Mac. The app does not run AI models on your phone. Chat, agent tasks, image/video generation, and collaboration run on your Apple Silicon Mac, while iPhone and iPad act as a mobile remote with a tailored UI. WHAT YOU CAN DO • Chat with MLX models loaded on your Mac • Remote agent and session history synced with the Mac web UI • Monitor operations (training, generation, jobs in progress) • Browse media generated on your Mac • Team / collaboration hub when enabled in MLX Studio • Home screen widget with Mac status (RAM, job, connection) HOW IT WORKS 1. Install and run MLX Studio on your Mac (Apple Silicon). 2. Enable MLX Link in MLX Studio’s Link tab. 3. Open MLX Companion on iPhone and complete pairing (QR on the same network or MLX Link relay). 4. Use the app anywhere: fast LAN at home, MLX Link relay (HTTPS) when away. REQUIREMENTS • Mac with MLX Studio installed and running • Apple ID for App Store (no MLX account required) • Initial pairing with your Mac PRIVACY Prompts and files stay on your Mac. The app only stores a pairing token in the iOS Keychain. MLX does not run inference in a cloud service. MLX Companion is an open-source companion app for MLX Studio users. It is not a standalone cloud chatbot.