I started building Clueprint after finding seven worktrees, four dev servers and a Docker stack I had no memory of starting. All spawned by Claude Code and Codex sessions from days earlier.
The app now watches all of it and tells me what's provably safe to stop. Launching here Sep 22.
Hey PH! I'm Mario. I built Clueprint because my own Mac was dying under the weight of my AI agents: every Claude Code session spawns a worktree, every worktree runs a dev server, and three weeks later you have 40 of them and your laptop fans spinning like crazy.
Cleanup only ever suggests things it can prove are safe (nothing uncommitted, nothing unpushed, branch merged, nothing running, idle 24h+), re-verifies at the moment you act, and archives instead of deleting. Files don't get deleted by Clueprint unless you say so.
I'd genuinely love to hear how it behaves on your setup, and what you'd want before 1.0.
Dude thanks for this, this is super useful! I just cleaned my computer and my mind a bit too. Found a project I forgot about, too :D
@bojan_opacak Thanks! Happy to see you feel the same about it - Clueprint is one of those projects that I as a founder and builder use myself, so I knew there'd be people who find it genuinely useful too. Much appreciated!
Uxia
the re-check before cleanup is the detail that makes this feel trustworthy. i've definitely had an agent leave a dev server running for days, curious how you handle projects with uncommitted changes that are intentional?