Lody vs AgentsDock

Lody is the remote control for your coding agents. Start a task from your phone, and Claude Code, Codex, or any CLI agent runs it on your own computer or server—then review every change, anywhere. ■ One remote for every coding agent • Works with Claude Code, Codex, Gemini CLI, OpenCode, Kimi, and any ACP-compatible agent • Bring your own subscription or API key—Lody runs the agents on your machines, with your models • Switch models, modes, slash commands, and Fast Mode right inside the chat ■ Control all your computers and servers • Connect every laptop, dev box, and cloud server to one account • Start a session on any online machine from your phone or browser • Machines stay private by default—share a build server or cloud worker with your team in one tap • Daemon mode keeps agents running in the background and recovers automatically after a restart ■ Run agents in parallel, safely • Every task gets its own isolated Git worktree—no collisions between parallel runs • Sandboxed execution with native runtime controls and fewer permission prompts • Session tabs keep the main chat, sub-agents, files, and diffs together in one view ■ Review everything from anywhere • Each turn ends with an in-context diff, so you can review without opening your IDE • A real-time file tree and project file browser stay synced with the working directory • Search inside a conversation across messages, tool calls, terminal output, and diffs • VS Code themes give you familiar code and diff colors • Lody Preview opens a live UI preview with desktop, tablet, and mobile viewports—drop visual annotations and send them straight back to the agent ■ GitHub, built in • Start a task from any Issue or Pull Request with a simple #mention • PR status, CI checks, and review comments sync automatically—no tab-switching • Mark drafts ready for review, merge, and delete branches without leaving Lody • Leave line comments on diffs and sync them to GitHub PR Review; replies post back both ways • Auto commit & push and "Fix PR comments" keep your branch moving • Act as yourself on GitHub for comments, reviews, and merges ■ Built for your team • Share agent configs and full conversation context so everyone stays aligned • Invite members, set roles, and view your teammates' sessions • Track AI token usage and cost by member ■ Made for mobile • Native iOS apps designed for small screens • Live Activities on iPhone show running agent status on the Lock Screen and Dynamic Island • Push notifications when a task finishes, an agent needs approval, or a PR is ready • Approve permissions, review diffs, and reply on the go • Works offline for cached conversations and saved diffs Install Lody on your machine, and take your coding agents with you—everywhere.

AgentsDock is the control surface for the AI agents you already run. AgentsDock talks to a small open-source server (AgentsServer) that you deploy yourself in one command. Every chat, job, and file stays on your infrastructure — and can be reached from anywhere. SYNCED ACROSS EVERY DEVICE Start a job on your Mac, check it from your iPhone or iPad, or drive it from Linux — every chat stays in sync in real time, wherever you are. RICH MEDIA, RIGHT IN THE CHAT Videos, simulation output, and image grids land directly in the conversation as your agent produces them. ALL YOUR CHATS, ORGANIZED Group work by project or folder, switch between Claude and Codex per chat, and keep every thread in one place instead of scattered across terminal tabs. FULLY SELF-HOSTED Run everything on your own Mac, Linux box, or cluster. Your code, credentials, and outputs never leave infrastructure you control. FULL TERMINAL, EVEN ON YOUR PHONE Each chat owns a persistent terminal session on your server — drop into a real shell from your phone whenever you need to. SCHEDULE JOBS AHEAD OF TIME Queue a run to fire now, after an interval, or on a repeating loop — kick off long research jobs without babysitting them. HAND OFF BETWEEN AGENTS Digest mode lets one chat summarize its work and send it straight into another, so long chains of work don't need manual copy-pasting. OPEN SOURCE SERVER AgentsServer is MIT-licensed and fully open source — read the code, fork it, and self-host it for as long as you like. The client is not open source yet. Requires a server you control running the AgentsServer installer, with Claude Code and/or Codex CLI already authenticated. AgentsDock does not include AI models or API access itself.