---
title: "pm2 ai agent: agents that keep a process running and read its logs"
description: "install pm2 on a room's server and its agents start long-running processes, list what is running, read the logs, and stop everything cleanly when work is done."
url: "https://aldena.ai/integrations/pm2"
---

# pm2 ai agent: agents that keep a process running and read its logs

pm2 solves a small problem that blocks a lot of work: an agent needs the app to still be running in the next message. installed on a room's server it puts `pm2` on the path for every agent in the room.

## what agents do with it

an agent starts a service with `pm2 start`, checks what is up with `pm2 list`, and reads accumulated output with `pm2 logs`. that last one matters more than it sounds. a background process that failed two requests ago left its stack trace somewhere, and pm2 is where the agent goes to find it. `pm2 kill` stops everything at the end, which keeps the room's machine in a known state for the next task.

## the matching skill

pm2 ships with a skill of the same name. it carries starting and listing processes, inspecting output with `pm2 logs`, stopping everything with `pm2 kill`, and the node.js dependency. skills load only for the agents you assign them to.

## example tasks

- **run the api in the background and check the webhook path works.**

  the agent starts the service under pm2 on the room server, calls the webhook from the same machine, and reads the process logs to confirm what arrived.

  tools: `bash` -> `read`

- **the worker keeps dying overnight. find out what kills it.**

  it reads the accumulated pm2 logs on the room machine, finds the unhandled rejection that ends the process, and fixes the handler.

  tools: `bash` -> `grep` -> `edit`

## what to know before installing

the room needs a paid server tier, and node.js must be installed first. pm2 is small and sits comfortably on the 4 gb tier alongside the app it supervises. uninstalling removes the global package from the room's machine.

## faq

### why does an agent need a process manager?

because a shell command ends when the command ends. pm2 start keeps the app running on the room's server between messages, so an agent can start a service in one step and call it in the next without holding a terminal open.

### what does the agent do with pm2 logs?

reads them. pm2 logs shows the output of a process that has been running in the background, which is how an agent finds the exception that happened three requests ago rather than only the one it triggered itself.

### does pm2 need anything installed first?

yes, node.js. the install script checks for npm and refuses with a message telling you to install the node.js technology first. installing node.js before pm2 avoids that round trip.

### will a process keep running and cost me money?

the process costs nothing on its own. the room's server is metered by the hour whether anything is running or not, so leaving a service up does not add to the rate. pm2 kill stops everything when the work is finished.