Sesori vs Unofficial OpenCode Client

Sesori is the remote control for the AI coding agents running on your own computer. Start a task at your desk, then follow it, answer it and steer it from your iPhone. Your code stays on your machine. Works with OpenCode, Codex, GitHub Copilot, Cursor, Claude Code, Pi, OMP, Hermes, DeepSeek and Grok Build. Sesori connects to the agents you already use; it is not affiliated with or endorsed by their makers. FROM YOUR PHONE • See every project and session on your computer, and run several sessions at once • Start a session, pick the agent and model, and give it its own Git worktree • Get a push notification when an agent finishes, asks a question or needs approval • Approve or reject permission requests where the agent supports them • Queue a follow-up while a turn is running, or stop it • Hold the mic and speak your prompt, then check the transcript before you send it • Attach images and use the agent's own slash commands and skills • Review the local Git diff, branch and pull request status PRIVATE BY DESIGN Your repository, toolchain and coding agent never move to a cloud workspace. The Sesori Bridge runs next to them on your computer and connects to your phone through a relay. Session traffic is end-to-end encrypted (X25519 key exchange, XChaCha20-Poly1305), so the relay passes ciphertext, not your code, prompts or AI responses. Voice transcription and notification previews use a separate, documented data path. HOW IT WORKS 1. Install Sesori Desktop on macOS or Linux and sign in. It runs the Bridge for you. On a server, over SSH or on Windows, run the headless Bridge CLI instead. 2. Sign in to this app with the same GitHub, Google, Apple or email account. 3. Your projects appear on your phone. Pick one and keep working. Not a mobile IDE and not a cloud sandbox: your agent runs where it always does, with your tools, files and settings. Your agent and model provider keep their own plans and pricing. Sesori is free. Setup guides and the security model: sesori.com and docs.sesori.com.

OpenCode Mobile is an unofficial, independent native client for the opencode server you run on your own computer. It is not made, published or endorsed by the opencode project. Start a session, follow it live, answer permission prompts and questions, and review changes while your AI coding agent keeps working at home. Nothing runs in our cloud. The app talks only to your own server. WHAT YOU CAN DO • Follow sessions live in Session Chat, with rendered Markdown and a tool-result inspector • Approve or deny permission requests and answer the agent's questions • Review diffs from the latest turn • Start work in worktrees and see them grouped under their project • Prompt with context: mention several skills, run shell commands with !cmd, attach files • Fork a session, or fork from a specific message • Open a live Terminal on your server and read project files • Dictate prompts by voice, recognised on your device • Use tablet split view with keyboard shortcuts • See a retry countdown and next steps when you hit a rate or usage limit • Pick your chat timeline (Standard, Chips, Step Rail or Activity Card), compact or classic Home, and a theme • Lock the app with optional App Lock CONNECT YOUR WAY • Remote QR: run opencode pair --remote on your computer and scan the code (OpenCode 2.0.25 or later) • Same Wi-Fi QR: let the server listen on your network, run opencode pair and scan • Host, username and password for OpenCode 1 and OpenCode 2 servers • Pairing code when the camera is not available Works over your LAN, a VPN, HTTPS, or a tunnel such as Tailscale. Step-by-step guide: https://opencode-mobile.github.io/opencode-mobile-docs/connecting/ PRIVATE AND OPEN • Your server password stays in iOS Keychain • The app does not host models or run your code • Release builds send crash reports through Firebase, and usage analytics you can switch off in Settings • The source code is public under GPL-3.0: https://github.com/opencode-mobile/opencode-mobile REQUIREMENTS A reachable opencode server and its password.