#26 · Primary category: AI Usage & Cost Monitoring
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
Project last updated:08/25/26
GitHub Stars
504
Forks
51
Contributors
5
License
MIT
Why we included this project
Anyone who lives inside Claude Code, Codex, or Kimi Code knows how easy it is to miss how many tokens a session actually burned until the quota or bill shows up. Token Tracker fixes that with a local, zero-config dashboard that reads each agent's own data files and shows usage, estimated cost, and remaining 5-hour and 7-day rate limits at a glance. Its cleverest trick is the status line: alongside official Claude Code support, it injects a two-line live bar into Codex, which has no native equivalent, so you see totals, cost, model, and context-window fill without leaving your editor. A side panel and a GitHub-style heatmap add session-level and daily/weekly cost views across projects and models. Everything stays on-device, which makes agent spending tracking easy to justify if you are privacy-averse.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
CodexBar
Show usage stats for OpenAI Codex and Claude Code, without having to login.
codeburn
Free, local tool to track AI coding token usage and cost across 37 tools and agents (Claude Code, Cursor, Codex, Gemini and more), by model, project, and task. npx codeburn
Claude-Code-Usage-Monitor
Real-time Claude Code usage monitor with predictions and warnings
helicone
🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓
agentsview
Local-first session search, analytics, insights, and token use statistics for coding agents, supporting Claude Code, Codex, and more than 20 other agents.