Agent Session Process Manager

A task manager for all your running AI coding sessions

Problem

Many developers run several Claude Code or Cursor agent sessions at once and quickly lose track of which is doing what, which is stuck, and which is burning credits. The terminal becomes a mess with no process view, forcing reliance on memory and window shuffling.

Solution

A local menubar/tray app that auto-discovers all active agent sessions and shows status (running, awaiting input, done, possibly stuck), model credit usage, and a summary of recent output. One click to interrupt, jump back to the terminal, or set a completion alert for long jobs.

Users

Heavy developers juggling multiple AI coding sessions; indie devs on metered billing worried about runaway spend; solo founders treating agents like employees.

MVP

Detect and group common agent processes on the machine; live status and recent output summaries; one-click interrupt and focus on the right window; system notifications when long tasks finish or fail; fully local, never uploads code.

Revenue

One-time purchase at $10-20, or $5/month subscription for cross-device sync and historical stats.

Why now

Running many sessions in parallel has shifted from a niche trick to normal practice, yet no OS-level helper exists. The scenario is too fresh for big vendors to have addressed it.