TokenTelemetry: model tool for Hermes Agent

Local dashboard for token usage, cost and tool calls across coding agents, with a dedicated Hermes Agent view

What TokenTelemetry does

TokenTelemetry reads the session logs that AI agents already write and shows token usage, LLM cost, tool-call waterfalls, plan-mode captures and reasoning steps in one dashboard. It lists Claude Code, Gemini CLI, Codex CLI, Cursor, GitHub Copilot, OpenCode, Qwen, Cline, Kimi Code and a number of other coding agents. Nothing leaves your machine, and no signup is needed.

Hermes Agent gets its own page at /hermes, because it runs across the CLI, messaging platforms, scheduled jobs and webhooks rather than only as a coding agent. The README says the Hermes view covers 38 source platforms, including Telegram, Discord and cron. Per-model analytics let you compare which model is most token-efficient on your codebase, and session cost tracking answers how much a given run cost. Installation is a one-line script for macOS and Linux or PowerShell for Windows.

Key features

Real-time cost and token tracking per session and project
Full waterfall trace of every tool call and captured plan mode
Per-model analytics and comparison across agents in one dashboard
Dedicated /hermes view covering 38 Hermes source platforms such as CLI, Telegram, Discord, cron and webhook
100% local with no signup and no cloud

When to use it

Finding out what a Hermes Agent running Telegram and cron jobs costs in tokens
Comparing token efficiency of different models on the same codebase
Getting one cost view when you use Hermes Agent alongside Claude Code or Codex

Who it is for: Developers who run several AI agents, Hermes Agent included, and want local visibility into tokens and cost.

How it fits with Hermes Agent

It supports Hermes Agent as one of many agents and adds a Hermes-specific dashboard, so it is a general tool with first-class Hermes coverage.

How to install TokenTelemetry

These commands are copied from the project's README. Check the repository for the latest steps before you run them.

curl -fsSL https://raw.githubusercontent.com/VasiHemanth/tokentelemetry/main/install.sh | bash
irm https://raw.githubusercontent.com/VasiHemanth/tokentelemetry/main/install.ps1 | iex

FAQ

What is TokenTelemetry?

TokenTelemetry is a free, open-source, local observability dashboard that tracks token usage, LLM costs, tool calls and session traces across AI coding agents and autonomous agents.

Does TokenTelemetry work with Hermes Agent?

Yes. Hermes Agent is listed as fully supported and has a dedicated dashboard at /hermes that covers 38 source platforms including the CLI, Telegram, Discord, cron and webhooks.

How do I install TokenTelemetry?

On macOS or Linux run the install.sh script from the repository with curl and bash. On Windows run install.ps1 with irm piped to iex. Both commands are in the install section.