Moru — A workspace for coding agents
Run coding agents in Moru, verify their work with Moru Core, and see your Mac and AI usage with Spill.
Stay with the work that matters.
Tell Moru what you want to change. See the work take shape, review the result, and decide what happens next.
Start with your project
Open the place where the work belongs.
Describe the change
Say what you want in your own words and follow its progress.
Make it yours
Review the result, then apply it, ask for a revision, or undo it.
One place to check and shape what your agents made.
Moru (모루) is Korean for a smith's anvil: the block where hot metal is laid down and hammered into shape. Working with coding agents needs the same kind of place. Their work should land somewhere you can see it, check it and shape it before you keep it. Moru is built around three gaps that show up once agents do real work.
Several agents, one view
With Claude Code, Codex and Antigravity open in separate terminals, it is easy to miss the one that is waiting for your answer.
Moru groups every agent session under its task, and the session that needs you turns amber.
“Done” that was never checked
An agent can say a task is finished without running the tests or reading the project's rules.
Moru Core keeps the task open until the checks it needs are recorded, and Moru Guard stops before risky steps.
Usage you cannot see
Tokens and remaining limits live in each tool separately, so you find out you ran out when an agent stops.
Spill shows every agent's usage and limits in the menu bar and in Moru's status bar.
Spill
A small panel in the menu bar for system status, AI token usage, Caffeine and window controls.
- CPU, memory and storage at a glance
- Local token usage for Codex, Claude Code and Antigravity
- Keyboard shortcuts to move windows to halves, corners and other displays
Moru
Describe a change, let several coding agents work on it in one window, then apply, revise or undo the result.
- Claude Code, Codex and Gemini in real terminals
- Shows which agent is working and which needs your answer
- Terminals and tasks are still there after a restart
Moru Core
Rules that tell a coding agent what to read, which steps a task needs and what to check before reporting it done.
- Works in your existing repositories
- Reads each project's own instructions first
- Does not report a task as done without recorded checks