#26 · Primary category: AI Usage & Cost Monitoring

token-tracker

ai-agent anthropic-claude claude-code cli codex cost-analysis developer-tools openai-codex python statusline terminal-ui token-tracker usage-tracking

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