E2B
SDK / ToolOpen-source secure sandboxes where AI agents run code — the de facto execution layer for agent apps.
- sandbox
- code-execution
- sdk
- agents
Token usage and cost analytics for Claude Code, straight from your local logs.
ccusage is the standard analytics tool for Claude Code spending: it parses your local Claude Code JSONL logs and reports daily/monthly/aggregate token usage and estimated costs per model, per session, and per 5-hour billing block. Fully offline — no API calls, no data leaves your machine. Run with npx ccusage@latest.
Answering how much your Claude Code usage actually costs, or which session ate the tokens, without wiring up a dashboard. An essential companion for Max-subscription users and API-key teams alike.
npx ccusage@latest # daily report npx ccusage@latest monthly # monthly view npx ccusage@latest blocks --live # 5-hour billing windows, live
Costs are estimates computed from token counts and public API prices — subscription usage isn't billed per token, so treat dollar figures as directional. Numbers are only as complete as your local logs.
Repository
ccusage/ccusageCharted
Open-source secure sandboxes where AI agents run code — the de facto execution layer for agent apps.
Pythonic framework for building MCP servers — decorators, type hints, and zero boilerplate.
Anthropic's official TypeScript SDK for building agentic applications.