Free for individual repos

Know what every AI agent run costs.

AgentMeter tracks token usage and cost for every GitHub Actions agent run — Claude Code, Codex, and GitHub Agentic Workflows — in one dashboard. Per-run costs, traced to specific issues and PRs. No infra. No config files. Three lines of YAML.

View on GitHub Marketplace

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

AgentMeter cost summary posted as a GitHub PR comment

AgentMeter runs feed showing cost, engine, status, and duration per run

AgentMeter run detail showing full token breakdown and cost

AgentMeter team settings showing connected repos and member management

Cost surfaces directly in your PRs — no dashboard required.

How it works

From zero to tracking agent costs in under 5 minutes.

Install

Install the GitHub App and add the AgentMeter Action from GitHub Marketplace to your existing agent workflow. Works with Claude Code, Codex, and GitHub Agentic Workflows (gh-aw) — no changes to your agent config.

Track

Every agent run is captured automatically — token counts, cost, duration, and GitHub context. A cost summary is posted directly on the PR or issue. No manual reporting.

See

Open the dashboard and see every run with full cost breakdown. Group by issue to see total feature cost. Spot expensive failures. Set budget alerts before you overspend.

Add in three lines

Drop this step after your existing agent action. No changes to your workflow logic.

.github/workflows/agent.yml

- name: Report agent costs
  uses: agentmeter/agentmeter-action@main
  if: always()
  with:
    api_key: ${{ secrets.AGENTMETER_API_KEY }}
    model: claude-sonnet-4-5
    status: ${{ steps.agent.outcome }}

View on GitHub Marketplace · Full docs & examples

Cost lands right on the PR

No dashboard required. Every agent run posts a cost summary as a PR comment — automatically.

agentmeter-botcommented2 minutes ago

⚡ AgentMeter — Run Summary

Workflow	Status	Tokens	Cost
agent-implement	✓ success	48,302	$0.58
agent-review	✓ success	12,891	$0.15
Total		61,193	$0.73

▶ Token breakdown (agent-implement)

Input: 32,100 ($0.10)

Output: 8,400 ($0.13)

Cache writes: 5,600 ($0.02)

Cache reads: 2,202 ($0.00)

14 turns · 62% cache hit rate

View in AgentMeter →

The comment is created on the first run and updated as more runs complete.

Simple, honest pricing

Less than the cost of a single agent run. Per-org, not per-seat.

Free

For individuals and open-source projects.

1 repository (your choice)
30-day data retention
Runs feed + run detail
PR cost comments
Claude & OpenAI models