AI product Open source

agentacct

agentacct is a local-first audit and observability tool for coding-agent work. It reads session logs from Claude Code, Codex, OpenCode, and Hermes, combines them with recorded tasks and test evidence, and produces a Work Receipt for each task covering commands run, files touched, tools used, time and token usage, cost, outcome, and evidence strength. Agent claims and machine verification are kept as separate axes, with verified status reserved for tasks whose live checks pass after the latest recorded work.

View repository Mentioned in 1 video ↓

Overview

The data is available through a macOS app, the live terminal dashboard launched with `agentacct tui`, and a local JSON API. State is stored in local files; the API listens only on loopback, and the project states that it has no login, cloud sync, or telemetry and does not request provider API keys.

What agentacct is used for

1 use taken from transcripts — each links to the moment in the video.

  • A local audit-trail tool for coding-agent sessions. It reads Claude Code and Codex logs, combines usage with tasks and test evidence, and shows tokens, estimated cost, and confidence-labeled work attribution in a localhost dashboard.

Videos mentioning agentacct

1 in the library.