Mossh vs AgentCmd

Mossh is an SSH terminal optimized for Codex, Claude Code, and remote AI coding workflows on iPhone. Connect to your remote development machine, attach to tmux, and keep long-running coding agent sessions available when you step away from your desk. Mossh is built for terminal-heavy work where readable diffs, logs, prompts, and command output matter. Save your SSH hosts, connect with a password or a generated key, and work in a terminal designed for mobile AI coding sessions. Mossh keeps the core workflow direct: open a host, trust the server key, continue your Codex or Claude Code session, paste safely, and get back to work. What you can do: - Save SSH host profiles with host, port, username, authentication method, TERM, startup directory, and tmux settings. - Connect with password authentication or an Ed25519 key generated and stored on your device. - Verify host keys before trusting a new or changed server. - Keep Codex, Claude Code, and shell sessions ready with tmux-friendly defaults. - Switch between multiple remote coding tabs and reconnect when needed. - Use readable terminal themes for code diffs, logs, prompts, and agent output. - Send common commands from a customizable terminal command panel. - Upload selected images or videos to the active SSH session and paste the remote file path. Mossh Pro is a one-time purchase. It unlocks unlimited hosts, up to 10 terminal tabs, unlimited custom commands, media upload, and the full terminal theme collection. The free version includes the core SSH workflow with limited hosts and one active terminal tab. Mossh does not include ads, analytics, or third-party tracking. Host profiles stay on your device, and passwords and generated private keys are stored in the iOS Keychain.

AgentCmd is a native remote control for the Qwen Code CLI's server (qwen serve) that runs on your own computer. Start the server in your project, pair your phone by scanning the QR code it prints, and drive your coding agent from anywhere on your network — or over a VPN or tunnel. It speaks the CLI's own protocol, so the phone shows exactly what the desktop does: • Live transcript — prompts, the agent's thinking, streamed replies, and every tool call as it happens, with token counts and timings. • Approvals on the go — approve or reject file edits and shell commands, with the diff or command right there. Choose how much to auto-approve per session. • Full agent toolbox — switch model and reasoning effort, browse and @-reference files, attach photos or files, and reach Plugins, Channels, Scheduled Tasks, Goals and workspaces. • Pick up any conversation — your sessions are listed newest-first; open one and its history is restored. • Notifications — get told the moment a task finishes, fails, or needs your approval, even while the app is in the background. • Yours end to end — the agent runs on your machine and this app talks only to it. No account, no analytics, nothing sent to us. Access tokens live in the device keychain; unencrypted HTTP is allowed only to local/private addresses. Requires the Qwen Code CLI (Node.js 22+) running qwen serve on your computer. Not sure yet? A built-in Demo shows a complete session offline, no server needed. AgentCmd is an independent client. It is not affiliated with, endorsed by, or sponsored by Alibaba or the Qwen team.