LLMPET

Desktop pet that reflects Claude Code/Codex agent status and tracks token spend

Desktopfree

LLMPET is an open-source desktop pet application that reflects the live status of a Claude Code or Codex coding session, such as thinking, working, waiting for approval, or finished, through changing expressions and speech-bubble replies. A details panel shows context usage, estimated cost, and session history, and Claude Code permission prompts can be approved or denied directly from the pet. It's aimed at developers who want an at-a-glance, ambient view of long-running AI coding sessions.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of LLMPET - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim LLMPET to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether LLMPET (or something else) actually fits.

Try a problem