Let your AI agents run
your dev environment.

# Every project, its running state, and active agents
lpm list --json

# One project's services, actions, and live status
lpm project myapp --full

# Live agent status across projects
lpm status

# Start or stop the whole project
lpm start myapp --profile full
lpm stop myapp

# Restart a single dev server
lpm service api restart

# Last 200 lines of a running service
lpm logs frontend -n 200

# Block until a port answers — no blind sleep loops
lpm wait --port 3000 --timeout 60

# Queue an action in a new lpm terminal
lpm run test --prompt "fix the failing spec"

# Post a custom status badge into the lpm UI
lpm set-status deploy "waiting on review"

exit 0 success·exit 2 not found / app not running·exit 1 error / timeout

# Clone into 3 copies, pull latest, and run the same prompt in each
lpm duplicate -n 3 --run claude \
--prompt "make the checkout flow pass its tests"

# Block until a copy's agent settles
lpm wait --agent -p myapp-copy-1

# Keep the winner, remove the rest
lpm remove myapp-copy-2

1. 01

   Fan out

   lpm duplicate -n 3makes three real, standalone copies of the project — a fast copy-on-write clone on Apple’s filesystem — groups them together in the sidebar, and queues the same agent and prompt in each.

2. 02

   Let them race

   Three agents attack the same task in parallel, each in its own copy with its own services and ports. lpm wait --agent -p <copy> blocks on each copy until its agent has finished — no polling loops.

3. 03

   Keep the best, clean up

   Compare the results, keep the copy you like, and lpm remove tidies up the rest. Copies are ordinary folders — nothing to unwind, no shared state to untangle.

• Can Claude Code restart my dev server?

  Yes. Once the lpm skill and CLI are installed, Claude Code can run lpm service <name> restart to bounce a single dev server, or lpm start / lpm stop for the whole project — then lpm wait to block until it is ready again.
• Which AI coding agents does this work with?

  Claude Code, Codex, Gemini CLI, and OpenCode. The skill is installed both for Claude Code and for the open agent-skills directory that Codex, Gemini CLI, and OpenCode read, so the same lpm commands work across all of them.
• Do I need MCP to connect agents to lpm?

  No. Agents drive lpm through a normal command-line tool. One click in Settings installs the skill and the lpm CLI together — there is no server to run and no MCP configuration.
• How does an agent know it is inside an lpm project?

  Every terminal inside lpm is tagged with the project it belongs to. The installed skill triggers whenever an agent sees it, so the agent automatically knows it can use the lpm CLI to drive that project — with no per-project setup.
• Can I run multiple AI agents in parallel on copies of a project?

  Yes. lpm duplicate clones a project into real standalone copies (up to 50) and can queue the same agent and prompt in each. lpm wait --agent blocks on a copy until its agent finishes, and lpm remove cleans up the copies you do not keep.
• Can agents read my dev-server logs?

  Yes. lpm logs <service> returns the recent output of any running service, so an agent can see the error it just caused and fix it. Nearly every command also supports --json for structured output, and exit codes are agent-friendly.
• Does this run on Windows or Linux?

  lpm is a native macOS app, so this is built for your Mac. There are no Windows or Linux builds.

Keep reading