agentacct

Local-first terminal dashboard showing what your coding agents did and what it cost.

Desktopfreeglobal

A local-first terminal dashboard that reads session logs from Claude Code and Codex to display usage, estimated cost, provider rate limits, and the actual work performed (steps, files changed, tests run) without requiring logins or sending telemetry. It helps developers get per-session cost and work attribution for coding agents and runs on macOS and Linux (Windows via WSL) with Python 3.11+.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of agentacct - 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 agentacct to unlock →

Try Matchbox with your own problem

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

Try a problem