Monitoring AI coding agent costs and activity on your own machine

Описание и применение

Разработчики, использующие несколько AI‑агентов, получили единый инструмент для отслеживания расходов, токенов и активности, что ускоряет диагностику сбоев и оптимизацию затрат.

Задача

Developers using multiple AI coding agents lacked a unified view of costs, token usage, and session activity, making it hard to diagnose slow or failed sessions.

Результат

Developers gain real‑time visibility into AI agent costs and activity, enabling faster diagnosis of failures and optimization of spending.

Рабочий процесс

• Install AgentMon Start on Windows/macOS/Linux
• Sign in via Codenotary
• Collector parses agent logs into snapshots
• Local server stores snapshots in SQLite
• Dashboard visualizes costs, token usage, tool calls, errors, and security findings
• Use session view to inspect threads, tool calls, and failures
• Use trace waterfall to debug stalled or unexpected sessions
• Set alerts for cost, error, and activity thresholds
• Review recommendations for cost and reliability improvements

Доказательства

I run Claude Code, Cursor, Codex and a handful of sub-agents on my own machines every day.

Источник

AgentMon Start reads the session logs your coding agents already write.

Источник

The Overview shows spending alongside session counts, token usage and cache hit rate.

Источник

The Tools view also aggregates failures across sessions, so you can see whether one tool accounts for most of the errors.

Источник

Alerts check every 60 seconds. Depending on your plan, they can flag cost thresholds, spending spikes, error spikes, long-running sessions and unmanaged agent activity.

Источник