---
title: AgentMeter — Local-first analytics and cross-tool comparison for AI
  coding agents — by Jad Madi (@jadmadi)
description: AgentMeter reads the session stores that Command Code, OpenCode,
  and Muse already write on disk, reconstructs per-step throughput, tokens,
  cache, cost, tool time, and session health, and renders filterable HTML and
  terminal reports. It compares any two tools with shared model-family pooling
  and explicit caveats. It is a single Go binary, read-only, offline, and sends
  nothing anywhere.
href: /project/agentmeter/
author: Jad Madi
category: Developer Tools & FinOps
domain: Developer Tools & CLI
status: Active Development
license: AGPL-3.0-only
year: "2026"
version: 2.0.0
---

# AgentMeter — Local-first analytics and cross-tool comparison for AI coding agents

AgentMeter reads the session stores that Command Code, OpenCode, and Muse already write on disk, reconstructs per-step throughput, tokens, cache, cost, tool time, and session health, and renders filterable HTML and terminal reports. It compares any two tools with shared model-family pooling and explicit caveats. It is a single Go binary, read-only, offline, and sends nothing anywhere.

## Project Overview

- **Website**: https://jadmadi.net/project/agentmeter/
- **Version**: 2.0.0
- **Live Platform**: https://jadmadi.net/project/agentmeter
- **Repository**: https://github.com/jadmadi/agentmeter
- **Documentation**: https://github.com/jadmadi/agentmeter/blob/main/README.md
- **Package**: https://pkg.go.dev/github.com/jadmadi/agentmeter
- **Domain**: Developer Tools & CLI
- **Category**: Developer Tools & FinOps
- **Status**: Active Development
- **Year**: 2026
- **License**: AGPL-3.0-only (copyleft)
- **Author**: [@JadMadi](https://x.com/jadmadi)

## Quick Install & Run

### Linux & macOS

```bash
go install github.com/jadmadi/agentmeter/cmd/agentmeter@latest
```

### Windows (PowerShell)

```powershell
go install github.com/jadmadi/agentmeter/cmd/agentmeter@latest
```

## The Problem It Solves

Developers running more than one AI coding agent cannot see how token spend, cache efficiency, latency, and session health compare across tools. The evidence sits in different local stores, in different shapes, and usually only surfaces one vendor at a time.

## The Solution

AgentMeter reads those local stores read-only, validates one schema v3 across tools, and renders per-tool reports plus like-for-like comparisons in a single static binary. It names the winner, shows the uncertainty, and marks cost and coverage caveats instead of hiding them.

## Key Features & Capabilities

- Per-tool reports for Command Code, OpenCode, and Muse covering throughput, tokens, cache, reasoning, cost, tool time, and session health
- Cross-tool comparison for any pair (oc-cmd, oc-muse, cmd-muse) with shared model-family pooling, output-size strata, explicit verdict confidence, and Simpson's-paradox detection
- Schema v3 fail-closed report and comparison builders plus independent Python oracle audits and fixture parity checks
- Read-only local readers: OpenCode SQLite, Command Code and Muse session JSONL; no prompts, assistant text, tool arguments, or file contents are read or emitted
- Embedded HTML dashboards and JSON/JS data files, with --serve and --watch, plus --json modes for cmd, oc, muse, and compare
- Per-tool wall-clock split into work and wait time, and per-model timed coverage that gates fixed-latency rankings
- Cost labels that mark recorded spend as a provider-reported floor and cache savings as a counterfactual, not a bill reduction
- Strict CLI behavior: date-window validation, fail-closed empty sources, actionable wrong-side report errors, ANSI-aware width adaptation, and documented exit codes 0/1/2
- Six cross-platform release archives for Linux, macOS, and Windows with checksums and AGPL, NOTICE, and third-party license texts

## Technical Specifications & Architecture

- **Languages**: Go, SQLite, Python
- **Frameworks / Libraries**: Go standard library, modernc.org/sqlite, Embedded HTML/CSS/JavaScript
- **Architecture**: Single static Go binary with read-only SQLite and JSONL readers, schema v3 fail-closed report and comparison builders, embedded HTML dashboards, and six cross-platform release archives
- **License Model**: AGPL-3.0-only

## Frequently Asked Questions

### Does AgentMeter send my session data to the cloud?

No. AgentMeter is local-first and zero-telemetry. It reads the local stores already on your disk, opens the OpenCode database read-only, and makes no network requests.

### Which tools can I analyze and compare?

Command Code, OpenCode, and Muse. Any two can be compared (`agentmeter compare`), and each tool also has its own report command (`agentmeter cmd`, `agentmeter oc`, `agentmeter muse`).

### How do I install AgentMeter?

Use a precompiled release archive from GitHub, or run `go install github.com/jadmadi/agentmeter/cmd/agentmeter@latest` with Go 1.26 or newer. `./build.sh --all` builds the same six archives locally.

### Why is recorded cost called a floor?

Recorded cost comes from what the provider reports. Free, contributor, and subscription-tier models may report $0, so per-step and per-1M figures can understate paid usage. Cache savings are a counterfactual at fitted prices, not money removed from a bill.

### Does AgentMeter read my prompts or code?

No. It reads usage, timing, model, and tool metadata. It does not read or emit prompts, assistant text, tool arguments, or file contents. Session titles and project names are included by default and can be suppressed with `--no-titles` and `--full-paths`.

## Links & References

- Project Page on Crosscurrent Code: https://jadmadi.net/project/agentmeter/
- Full Projects Directory: https://jadmadi.net/projects/
- Author Profile: https://jadmadi.net/about/