#12 · Primary category: AI Usage & Cost Monitoring
token-monitor
Local-first desktop widget for tracking token usage, costs, and limits across 33+ AI coding tools—including Claude Code, Codex, Cursor, OpenCode, and OpenClaw—with multi-device sync.
Project last updated:08/29/26
GitHub Stars
1.8K
Forks
169
Contributors
35
License
MIT
Why we included this project
Token usage is easy to lose track of when you spread your work across several AI coding tools and more than one machine. Token Monitor is a desktop widget that reads the local logs and databases of Claude Code, Codex, Cursor, Copilot, and two dozen other tools, then shows usage, cost, and provider limits in one view. It is local-first: each device watches its own data and only sends lightweight summaries to a hub, so your transcripts never leave the machine. The per-session drill-down lets you open a single Claude Code or Codex session and see the exact token split per reply, cache hits versus misses, and which tools were used. Teams juggling multiple accounts or providers get one-click Codex account switching and provider-specific limit windows for weekly or billing caps.
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.