GitHub - MrQianjinsi/agentic-metric: A local-only monitoring tool for AI coding agents.
github.com
A local-only monitoring tool for AI coding agents. - MrQianjinsi/agentic-metric

I’d like to introduce agentic-metric, a local-only monitoring tool for AI coding agents — essentially like top, but for your coding agents.

Key Features

  • Live Monitoring — Detect running agent processes with incremental JSONL session parsing
  • Cost Estimation — Per-model pricing table that calculates API-equivalent costs
  • Today’s Overview — Sessions, token usage, and cost summary for the current day
  • Historical Trends — 30-day daily token/cost trends
  • TUI Dashboard — Terminal UI with 1-second live refresh, stacked token charts, and trend lines
  • Multi-Agent Support — Plugin architecture supporting Claude Code, Codex, OpenCode, Qwen Code, VS Code, and more

Privacy First

All data stays on your machine. No network requests, no telemetry, no data leaves your computer. The tool only reads local agent data files (e.g. ~/.claude/) and process info.

Installation

pip install agentic-metric

Usage

agentic-metric              # Launch TUI dashboard (default)
agentic-metric status       # Show currently active agents
agentic-metric today        # Today's usage overview
agentic-metric history      # Historical trends (default 30 days)
agentic-metric sync        # Force sync data to local database
agentic-metric bar         # One-line summary for status bars

Perfect for developers who want to track their AI coding agent usage and costs while maintaining complete privacy and control over their data.

Check out the repository at: https://github.com/MrQianjinsi/agentic-metric