📝 Launch blog · 🌐 Website · 📚 Learn Tokenomics

Token Meter is an open-source, local-first usage and cost dashboard for AI coding agents. It shows token usage, estimated cost, context pressure, time, and tool activity for Claude, Codex, Cursor, OpenCode, Kiro, and Pi in one place.

• Local only. Python standard library, no API keys, no telemetry.
• Honest numbers. Estimates are labelled; missing evidence stays unavailable, never zero.

Things your bill won't tell you

• 6% of tokens were 55% of the dollars. On Claude Opus 5.5, cache writes cost 25 times as much as cache reads.
• 83,907 tokens of tool definitions were loaded into prompts and never called.
• Subagent runs fell from $6.04 to $0.96 each in a month, by giving them short, narrowly scoped tasks.
• Cutting xhigh reasoning from 70% to 22% of spend helped lift output per dollar 73% in three months.

These numbers come from one engineer's laptop, estimated at public list prices. Yours will differ.

Read: Five levers that move your coding-agent bill

Quick Start

macOS or Linux

git clone https://github.com/splunk/token-meter.git
./token-meter/scripts/install

This starts the local server and native companion, and enables automatic startup. Add --backend-only to skip the menu-bar/tray companion.

Windows

Beta: the Windows extension is still in beta.

powershell.exe -NoLogo -NoProfile -ExecutionPolicy Bypass -Command '$p=Join-Path $env:TEMP "token-meter-bootstrap.ps1"; try { Invoke-WebRequest -UseBasicParsing "https://raw.githubusercontent.com/splunk/token-meter/main/scripts/bootstrap-windows.ps1" -OutFile $p; & $p } finally { Remove-Item -LiteralPath $p -Force -ErrorAction SilentlyContinue }'

The bootstrap uses WinGet (App Installer) to add any missing Git and Python, with no administrator access. From a checkout, run .\scripts\install-windows.cmd. Add -BackendOnly (& $p -BackendOnly) to skip the notification-area companion.

The notification-area companion includes a floating usage panel. Drag it to move it, or hide it from its context menu; its position and visibility persist across installs and updates. Running run-tray.ps1 directly backgrounds it; -Inline is the installer-managed launch mode.

Uninstall: powershell.exe -NoLogo -NoProfile -ExecutionPolicy Bypass -File "$env:LOCALAPPDATA\Token Meter\runtime\scripts\uninstall-windows.ps1"

Open the dashboard

Go to http://127.0.0.1:8722, start an agent run, and pick it under Sessions. Requirements, updates, uninstall, and troubleshooting are in the User guide.

Platforms

Platform	Status	Companion
macOS	Supported	Menu bar
Linux	Supported	AppIndicator tray
Windows	Beta	Notification area

Runtimes: Claude Code and Desktop (Agent/Cowork), Codex CLI and desktop, Cursor Agent/Composer, OpenCode, Kiro, and Pi. Only sessions stored locally are visible.

OpenCode's current storage (the session_v2 tables OpenCode adopted in October 2026) and older pre-V2 databases are both supported: Token Meter reads the V2 store when present and falls back to the legacy tables otherwise. OpenCode databases are only ever opened read-only.

Features

Follow a session

Live cost, tokens, context pressure, output pace, tool calls, session budgets, and child-agent activity on one page.

Understand spend

Compare any period across platforms, projects, runtimes, and sessions to find the runs worth inspecting.

Check efficiency

Signal	Meaning	Better
Output / $	Output tokens per dollar	Higher
Reasoning ratio	Reasoning share of output	Lower or stable
Context load	Input tokens per output token	Lower
Cache hit ratio	Cache-read share of input	Higher

Inspect tools and skills

Spot high-output, failing, repeated, or unused tools and skill packs.

Git

Pairs local pushes with spend to show code changed per project and day, using local git only. A mechanical signal, not a productivity score.

Subagents

Track spend, cost per run, and volume for each named child-agent role, and drill into individual runs from Sessions → Subagents.

Goals

Set a target for Spend, Output / $, Cost per 1K pushed lines, Context load, Reasoning ratio, Frontier share, or Tokens used from Efficiency → Goals. Choose an app and one or more models, a period, and a target based on your previous usage. Inspect goal charts by hovering or using arrow keys. Delivery contributors show repository spend and lines pushed; coverage explains which repositories count. Hold your current level, repeat calendar goals, or duplicate a previous goal. Progress also shows on Spend, Git, and the menu bar or tray. See goal measurements.

Budgets, settings, and MCP

Set monthly and per-session budgets, edit model pricing, and connect Codex or Claude to the local MCP: eight read-only evidence tools (check, usage, budget, capabilities, sessions, trace, stats, schema) plus two session-budget setters that require confirm: true. Traces are allowlisted structure and numbers, not raw trace content. See the User guide for details.

Menu bar and tray

See the current run without opening the dashboard. Updates are checked every 10 minutes and installed automatically by default.

Privacy

• The dashboard binds to 127.0.0.1. Do not expose it publicly.
• Traces, prompts, responses, paths, and analytics never leave your machine.
• The MCP returns derived numbers only. Agents you connect may send them to their model provider.
• Costs are estimates. Codex uses public API rates, which can differ from subscription billing.

Full details: User guide · Security policy.

Documentation

Document	Covers
User guide	Setup, daily use, MCP, updates, troubleshooting
Cost estimates and budgets	How reliable costs are, converting credits into agent budgets
Security	Privacy boundaries, vulnerability reporting
Architecture	Components, data flow, extension contracts
Contributing	Issues, pull requests, validation
Product · Design	Product and experience decisions

License

MIT. See LICENSE.