uttamdeb

Agent Telemetry — Data skill for Claude Code

Data community

Live local dashboard for AI coding-tool usage — Claude Code, Claude Desktop, Codex, GitHub Copilot, Cursor, opencode.

How to install Agent Telemetry

This entry records only its repository, not the path inside it, so there is no exact command to give. Open uttamdeb/agent-telemetry and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Agent Telemetry does

Live local dashboard for AI coding-tool usage — Claude Code, Claude Desktop, Codex, GitHub Copilot, Cursor, opencode. Zero deps; your data stays on your machine.

Alternatives in Data

Claude Code Usage Monitor — by Maciek-roboblog - A real-time terminal-based tool for monitoring Claude Code token usage 7k ★
Claude Deep Research Skill — Enterprise-grade deep research skill for Claude Code with 8-phase pipeline, source credibility scoring, and au 1k ★
Memex — Open-source, local-first AI journal app for iOS and Android 697 ★

README

AgentTelemetry

**Live, local telemetry for your AI coding agents.** AgentTelemetry reads the interaction logs your tools already write to your own machine and serves a clean, interactive dashboard — estimated spend, tokens, active time, cache efficiency, an **Anthropic vs OpenAI vs Google** provider comparison, an activity calendar, and breakdowns by **model, provider, day, hour, weekday, tool, IDE, project and session** — plus how much **disk** all these logs eat, and suggestions for spending less, drawn from your own numbers.

**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 · Hermes Agent · OpenClaw**.

Quick start

git clone https://github.com/uttamdeb/agent-telemetry.git
cd agent-telemetry
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]`.

`--rebuild` deletes the cache, and with it every session whose log has since been deleted from disk (see [Storage](#storage--what-these-logs-cost-you-in-disk)). Copy `.usage_cache.json` somewhere safe first if you've cleaned up old logs.

**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_*`,