Coding Agent Usage

AI Usage Dashboard

A **live, local** analytics dashboard for your AI coding-assistant usage. It reads the interaction logs your tools already write to your own machine and serves an interactive dashboard — tokens, estimated cost, cache efficiency, an **Anthropic vs OpenAI vs Copilot** provider comparison, a GitHub-style activity calendar, and breakdowns by **model, provider, day, hour, weekday, tool, project and session** — plus how much **disk** all these logs eat.

**Your data never leaves your machine.** No account, no API key, no telemetry, no dependencies — just Python's standard library and a vendored copy of Chart.js.

Covers **Claude Code · Claude Desktop · Codex · GitHub Copilot · Cursor · opencode**.

---

Quick start

git clone https://github.com/uttamdeb/coding-agent-usage.git
cd coding-agent-usage
python3 dashboard.py

Then open **http://127.0.0.1:7878**. That's it — no `pip install`, no setup.

First run parses your local logs (can take ~30–60s if you have large Codex logs), writes a cache, and is instant thereafter. The page auto-refreshes every ~15s, so a session you're running *right now* shows up within seconds.

Options: `python3 dashboard.py --port 9000` · `--rebuild` (ignore cache, full re-parse) · `--interval 20` (background refresh seconds). Or `./run.sh [flags]`.

**Requirements:** Python 3.8+ on **macOS, Linux or Windows**. On Windows run `python dashboard.py` (or `run.cmd`); on macOS/Linux `python3 dashboard.py` (or `./run.sh`).

It works on anyone's machine because **nothing is hardcoded** — every location is derived at runtime from your own `$HOME` / `%APPDATA%` / `%LOCALAPPDATA%` / `$XDG_*`, the numbers are read live from your own logs on every refresh, and the disk figures come from your own drive. Two people running this see two completely different dashboards.

---

Everyone sees *their own* usage

This is the important part if you're sharing it: the dashboard has **no bundled data**. On each machine it scan