Native desktop terminal for AI agents
The native macOS terminal
for Claude Code and Codex.
A native macOS app with live output per service in one window. Watch multiple agents work side by side and switch projects visually — without juggling a wall of terminal tabs.
Projects, terminals, Claude Code or Codex — one click each
Click anywhere below. Switch projects, start services, launch Claude Code or Codex — all running live in your browser, right now.
Running agents in parallel breaks a regular terminal
One AI coding agent is easy. Two or three working side by side on real projects is where the wheels come off — you need a workspace built for it.
Port conflicts everywhere
Two agents spin up the same dev server and race for port 3000. One wins, one crashes, and you spend more time restarting than coding.
No idea who is doing what
Five terminal tabs, five agents, and no clear view of which one is running tests, which is waiting, and which just errored out.
Context vanishes on every switch
Jump to another project and your running services, logs, and agent sessions are gone. Coming back means rebuilding the whole stack from memory.
A native workspace for the agents doing your work
Every service, side by side
Watch live terminal output from every service in one window. No more tab-juggling to find which agent broke the API while the other is editing the frontend.
Visual project sidebar
Every project sits in the sidebar. Click to jump straight to one with agents already running — no hunting through terminal windows.
Built-in config editor
Edit a project's config inside the app and restart services on the spot. No digging through dotfiles to tweak what an agent is running.
One-click actions
Wire up buttons for tests, lints, and deploy scripts. Run them with a click while the agent keeps working next door.
Toggle service profiles
Flip between profiles from the app header to run just the services the agent touches — or spin up the full stack when you need it.
Native, dark, and fast
A real macOS app with dark mode, native speed, and no browser tab eating your battery while agents chew through your codebase.
What changes when you run agents in a real macOS window
Every agent in one window, not five tabs
Watch Claude Code, Codex, and your whole dev stack from a single macOS window. No more hunting through terminal tabs to find the one that errored.
See which agent broke what, in real time
Live output per service, side by side. Spot the moment one agent breaks the API while the other is still editing the frontend.
Jump between projects visually
Switch projects with a click instead of asking "which tab was that again?". Your running services and logs follow the project you're on.
Native macOS, not a browser tab
A real desktop app with dark mode, fast startup, and a built-in config editor. Stays out of the way while your agents do the work.
Workflows that used to be painful
Claude Code on a feature branch, Codex writing tests
Click Start on your project in the lpm sidebar and the full stack boots in one window, one service per tab. Point Claude Code at it to drive the feature work, then flip the profile dropdown in the header to a lighter test profile and point Codex at that. Two agents, the same repo, no fighting over port 3000 — and you can watch both of them work by glancing at the live service tabs side by side.
Switch branches without a stale dev server
Agents get confused when the server on port 3000 is still running the code from the branch they just left. Hit Stop on the project in the sidebar and everything shuts down cleanly — no orphaned node processes, no stuck migrations. Click Start again on the new checkout and the whole stack comes back fresh in the same window, so when Claude Code returns it sees the code it actually expects.
Give the agent only the services it should see
You don’t need the Next.js frontend running while an agent is refactoring a Go API. Open the profile switcher in the header and pick a profile that only exposes the API and its database — the frontend tab drops out, the API keeps running, and the agent works against a smaller, quieter stack. Fewer moving parts, less terminal noise, and no accidental writes to services the agent was never meant to touch.
A desktop workspace, not another terminal
The lpm macOS app gives every running service its own pane in one native window — the visual layer your terminal tabs, tmux session, or editor doesn't.
| Capability | lpm desktop | Terminal tabs | tmux / screen | Editor window |
|---|---|---|---|---|
| Start full stack in one command | ||||
| Live output per service | ||||
| One window for every running service | ||||
| Run multiple agents in parallel with no conflicts | ||||
| Visual project switcher with live state | ||||
| Native macOS app with dark mode |
lpm desktop
- Start full stack in one command
- Live output per service
- One window for every running service
- Run multiple agents in parallel with no conflicts
- Visual project switcher with live state
- Native macOS app with dark mode
Terminal tabs
- Start full stack in one command
- Live output per service
- One window for every running service
- Run multiple agents in parallel with no conflicts
- Visual project switcher with live state
- Native macOS app with dark mode
tmux / screen
- Start full stack in one command
- Live output per service
- One window for every running service
- Run multiple agents in parallel with no conflicts
- Visual project switcher with live state
- Native macOS app with dark mode
Editor window
- Start full stack in one command
- Live output per service
- One window for every running service
- Run multiple agents in parallel with no conflicts
- Visual project switcher with live state
- Native macOS app with dark mode
Questions developers ask before switching
Does lpm work with Claude Code and Codex out of the box?
Yes. You point lpm at your project, hit Start in the app, and watch each service stream live output in its own pane. The agent talks to the services the app started.Can I run multiple agents in parallel on the same repo?
Yes. Each project gets its own entry in the app sidebar with live panes per service, so Claude Code on one stack and Codex on another sit side by side — every agent's output visible at once, no tab juggling.Do I need Docker to use lpm?
No. lpm runs anything that runs in a terminal. If you already use Docker Compose it is auto-detected, but plain Rails, Next.js, Go, Django, or Flask projects work without containers.Is lpm open source?
Yes. The source, issue tracker, and releases live on GitHub. Contributions and bug reports are welcome.Which frameworks does lpm auto-detect?
Rails, Next.js, Go, Django, Flask, and Docker Compose are detected out of the box. Anything else still works — if it runs in a terminal, lpm can start it.Is there a CLI, a desktop app, or both?
This page is about the native macOS desktop app — tabs, live output per service, and a visual project switcher are the main pitch. A CLI is also available and shares the same config if you want to script things or drive lpm from an agent.
Download the macOS app.
Run your agents side by side.
Native desktop workspace for Claude Code, Codex, and every other agent that lives in a terminal.