#18 · Primary category: AI Usage & Cost Monitoring
onWatch
Track AI API quotas across Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigravity in real time. Lightweight background daemon (<50MB RAM), SQLite storage, Material Design 3 dashboard. Zero telemetry.
Project last updated:08/20/26
GitHub Stars
722
Forks
63
Contributors
17
License
GPL-3.0
Why we included this project
Anyone who pays for more than one AI coding service has probably been cut off mid-task by a quota they forgot to check. onWatch is a small background daemon that tracks usage across Anthropic, Codex, GitHub Copilot, and other providers, so you can see how much budget is left and when the reset window opens before you get throttled. Everything is stored locally in SQLite and shown in a Material Design dashboard, with alerts and burn-rate views that make it easy to switch to a provider that still has headroom. It uses little memory and sends no telemetry, which matters if you want cost visibility without shipping your usage data anywhere. If you juggle several AI subscriptions, this gives you one place to watch the quotas.
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.