@DanKornas: AI coding-agent spend is easy to lose track of when usage is spread across tools. ccusage is a command-line tool for de…
Summary
ccusage is an open-source command-line tool that helps developers inspect token usage and costs from local coding-agent CLI data, offering daily/weekly/monthly reports, model breakdowns, and JSON export.
View Cached Full Text
Cached at: 07/31/26, 07:01 PM
AI coding-agent spend is easy to lose track of when usage is spread across tools.
ccusage is a command-line tool for developers who want to inspect token usage and costs from local coding-agent CLI data.
It helps you turn local data into daily, weekly, monthly, and session reports across detected sources, with JSON, date-range, and timezone options.
Key features: • Multi-agent reports – combines detected CLI sources in one report • Time-based views – groups usage by day, week, month, or session • Cost visibility – shows USD costs and can hide cost columns with –no-cost • Model breakdowns – tracks models and supports per-model cost breakdowns • Structured output – exports report data as JSON for other workflows
It’s open-source (MIT license).
Link in the reply
Similar Articles
@DanKornas: Coding agents can say “done.” This repo gives you a receipt. agentacct is a local-first work-intelligence dashboard for…
agentacct is an open-source, local-first dashboard for developers to review tasks performed by coding agents like Claude Code and Codex, generating detailed work receipts with actions, costs, and evidence.
Show HN: Frugal Tokens – explore costs and usage across coding agents
Frugal Tokens is a tool for analyzing costs and usage patterns across coding sessions with AI models, helping developers understand and optimize their spending.
CodeBurn
CodeBurn is a tool that shows where your AI coding spend actually goes, helping developers track and analyze AI-related costs.
@akshay_pachaar: https://x.com/akshay_pachaar/status/2053166970166772052
The article discusses a shift in AI agent tool usage from the 'MCP vs CLI' debate to 'Code Mode,' where agents write code to dynamically import tools, significantly reducing context window usage. It highlights Anthropic's approach and Cloudflare's implementation, demonstrating a 98.7% reduction in token consumption for specific tasks.
kenn-io/agentsview
agentsview is an open-source local tool for browsing, searching, and tracking costs across AI coding agents.