Orca runs several coding agents at once, each in its own git worktree, and tracks them in one window. You can fan one prompt out to several agents, compare the results and merge the best. It has terminal splits, a VS Code-style editor, a built-in Chromium window whose Design Mode sends a clicked element to the agent, GitHub and Linear tasks, diff comments you send back to the agent, and SSH worktrees on a remote machine.
It works with any agent that runs in a terminal, including Claude Code, Codex, Cursor, Grok and GitHub Copilot. There are builds for Apple silicon and Intel Macs, and an iPhone and iPad companion (iOS 15.1 or later) that notifies you when an agent finishes and lets you send follow-ups.
Orca is free and open source under the MIT licence. Your code stays on your Mac or your own SSH host; prompts go to the agents and model providers you use. Orca collects anonymous usage data, which you can turn off.
Official downloads only. MLX never re-hosts an app, and never runs a command for you.
Ranked against the agents & automation listings, from real public data only. How the score works.
Orca is a product of Stably AI; MLX isn’t affiliated with it. Something wrong? Write to support@mlx.app.