Tokimeter is an open-source, local usage analytics tool designed specifically for developers using various AI coding assistants. By pulling the usage records that your AI coding tools already write to your machine, Tokimeter aggregates them into comprehensive, unified reports.

With Tokimeter, you can easily track exact token counts and associated costs broken down by project, session, day, tool, and model. It also monitors 5-hour and weekly limit windows, providing helpful budget warnings directly in your status line to help you manage your AI tool usage efficiently.

Designed with privacy in mind, Tokimeter requires no account and zero telemetry—everything stays securely on your local machine. It supports a wide range of platforms including Claude and Codex (both CLI and desktop apps), Cursor, Grok Build, Hermes, opencode, Cline, and Copilot CLI. You can generate a report instantly using npx tokimeter report under an MIT license.

Pros of Tokimeter

Local-first architecture with zero telemetry; nothing leaves your machine
Requires no account setup or configuration
Comprehensive coverage of popular AI tools like Claude, Codex, Cursor, Grok Build, and more
Tracks exact token counts and costs by project, session, day, tool, and model
Open-source and MIT licensed

Cons of Tokimeter

Limited to tools that write local usage records
Requires using the command line interface (e.g., npx) to generate reports
Relies on supported tool ecosystems mentioned in the metadata

Frequently Asked Questions

What is Tokimeter?

Tokimeter is a local usage analytics tool for AI coding assistants that consolidates your usage records into a single report, tracking token counts, costs, and limit windows.