AgentReceipt

AgentMeter Alternative: PR Cost Comments That Explain the Cost

AgentMeter posts what an agent run cost on the PR. AgentReceipt does that too, and adds why: idle-gap cache misses, retry loops, oversized tool output, with what fixing each would save.

What AgentMeter is

AgentMeter is a GitHub Action that records the cost of AI agent runs and comments on pull requests, free for one repo.

Where AgentMeter is the better fit:

  • Simple GitHub Action setup
  • PR comments with run cost

What AgentReceipt does differently

  • A per-step explanation of the cost with savings figures
  • Works locally too: Claude Code SessionEnd hook, Codex, and a no-install browser analyzer
  • Share links and a workspace dashboard with waste %, cache hit rate and cost by model

Pricing

AgentMeter is free for one repo; paid pricing was not published at the time of writing.

Product details change; check each vendor’s site for current features and prices. Many teams use both: an observability platform for their own LLM apps, and AgentReceipt for coding-agent spend per task.

Itemize your own session

Drop a Claude Code or Codex log. It is parsed in your browser, and you get your real numbers instead of a model.

Drop a session log here

Claude Code ~/.claude/projects/…/*.jsonl, a Codex rollout ~/.codex/sessions/…/rollout-*.jsonl, or the claude-code-action execution file.

Parsed in your browser. Your prompts and code never leave this tab.