Free for individual repos

Your AI coding bill shouldn't be a surprise.

See what every Claude Code and Cursor session actually costs — per engineer, per project, per task. Plus your CI agent runs. All in one dashboard.

Install free

By signing in you agree to our Terms and Privacy Policy.

AgentMeter runs feed showing local and GitHub Actions sessions with cost, engine, source, status, and quality score

AgentMeter run detail page showing run metadata, status, cost, and quality rating

AgentMeter run detail token breakdown showing input, output, and cache costs

AgentMeter trends dashboard showing spend over time broken down by source, project, engine, and contributor

AgentMeter contributors dashboard showing per-engineer spend, run counts, and connection status

AgentMeter contributor detail page showing spend over time and run history for a single engineer

Every session and CI run in one feed — local or GitHub, cost, engine, status, and quality score at a glance.

Drill into any run: what it did, what it cost, and how good the result was. Rate quality to track whether spend is paying off.

Exact token costs per run — input, output, and cache. Know precisely where every dollar goes.

See spend break down by source, project, engine, and engineer. Know that local sessions are 31% of your AI bill — or that one teammate is driving a third of it.

Score run quality against cost. Find out which models and workflows are actually worth what you're paying.

See who on your team is spending what — per-engineer cost, run counts, and live connection status in one view.

Drill into any contributor: their spend trend over time, run history, and how their usage compares to the team.

Two ways to track. One dashboard.

Local sessions

Track Claude Code and Cursor sessions on every engineer's machine. A lightweight CLI scans local data — no API keys shared, no proxying.

npx @agentmeter/cli init

Most teams start here

CI agent runs

Track GitHub Actions agent runs — gh-aw, Claude Code Action, Codex. One step in your workflow posts a cost summary right on the PR.

- uses: agentmeter/agentmeter-action@main
  with:
    api_key: ${{ secrets.AGENTMETER_API_KEY }}

See everything

Local Claude Code and Cursor sessions, plus GitHub Actions agent runs, in one feed. Token-level cost breakdowns for every run.

Know who and what

Costs attributed to engineers, projects, workflows, and tasks. Know that issue #47 cost $12.40, or that a teammate’s sessions ran $284 this month.

Spend wisely, not just less

Ratings score run quality against cost. Find out whether your most expensive runs are actually your best ones.

The problem isn't spending. It's visibility.

No one could see the spend accumulating until the bill arrived.

Uber burned through its entire 2026 AI budget in four months. Microsoft revoked Claude Code licenses across its engineering org. The FinOps Foundation calls it “existential crises.”

The common thread isn't overspending — it's that no one could see the spend accumulating until the bill arrived.

AgentMeter is the visibility layer. Per-engineer, per-project, per-task — before the bill, not after.

Read the full story →