Usage Tracking Python Packages

claude-statusbar

Lightweight Claude Code statusLine: 5h/7d rate-limit usage, reset countdowns, model + context window, prompt-cache age — one line, 3 styles × 9 themes, daemon fast-mode

sandhi-gateway

Sandhi — the metering layer for AI agents. An open-source AI usage gateway: meter, attribute, and budget every model call across shared keys.

claude-jacked

Hit a Claude Code usage limit and jacked switches accounts for you. Multi-account manager and skills suite for Claude Code and Codex: live 5h/7d usage tracking, auto account-switching, a menu-bar app on macOS and system tray on Windows/Linux, plus 30 slash commands, 28 skills and 10 review agents from a web dashboard.

claude-monitor

Real-time Claude Code usage monitor with predictions and warnings

streamlit-analytics2

Privacy-first usage analytics for Streamlit apps: pageviews, visitors, widget clicks, custom events, built-in dashboard, SQL over your own data. No JavaScript, no cookies.

token-tracker

Claude Code & Codex 本地 token 追踪 — 状态栏（Codex 业界首创伪 statusline）、GitHub 风格热力图、多模型成本分析。 | Local token tracker for Claude Code & Codex — status line (industry-first Codex faux statusline), GitHub-style heatmap, multi-model cost analysis

audr-adapter-nemo-relay

Agent Usage Detail Record — an open JSON standard for attributing and costing agent runs

ccstory

Claude Code usage recap with narrative. ccusage tells you the bill, ccstory tells the story.

headroomhq

Self-hosted dashboard for all your AI plans. Track limits, resets and spend across Claude, Codex, Cursor, Copilot, Grok and more.

audr-adapter-litellm

Agent Usage Detail Record — an open JSON standard for attributing and costing agent runs

audr

Agent Usage Detail Record — an open JSON standard for attributing and costing agent runs

audr-sink-chargebee

Agent Usage Detail Record — an open JSON standard for attributing and costing agent runs

claude-usage-dashboard

Local dashboard for Claude Code usage: hours, tokens, project split, and a weekly-limit gauge calibrated from your own /usage readings

cctrail

CLI for analyzing local Claude Code and Codex history by token usage, cost, active time, projects, and groups.

dashboard-for-claude-code

A local Claude Code dashboard for personal analytics: track token usage, API-equivalent cost, sessions, tools, skills, projects, and activity patterns.

claudron

Your Claude limits reset 5 hours after your first message. Decide when that is.

claude-usage-monitor

Real-time Claude Code usage monitor with predictions and warnings

ccbar

A lightweight, per-project tracking cost & quota statusline for Claude Code with zero dependencies.

trackly

Zero-overhead AI cost and usage tracking for Python. Import the library, wrap your LangChain model, and every LLM call is automatically logged - tokens, cost, latency, and your own metadata.

cc-telemetry

Centralized Claude Code usage tracking across multiple PCs — web dashboard with 5-hour blocks, rate limits, cost analysis, and multi-machine aggregation

miscreaders

Parsers for output of various programs