onWatch
Track AI API quotas across Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigravity in real time. Lightweight background daemon (<50MB RAM)
What is 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.
Overview of onWatch
What it is
onWatch is a free, open-source AI API quota monitoring tool for developers. It tracks usage across multiple AI providers in real time, running as a lightweight background daemon (under 50 MB RAM) with SQLite storage and a Material Design 3 dashboard. The tool has zero telemetry and operates entirely locally.
Key features
- Tracks usage across Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot, MiniMax, Gemini CLI (legacy), Cursor, Grok, Kimi Code, and Antigravity.
- Provides historical usage trends, reset cycle detection, per-cycle consumption stats, usage rate projections, per-session tracking, and live countdown timers.
- Material Design 3 dashboard with dark/light mode, provider-specific quota cards (e.g., Synthetic subscription/search/tool call, Anthropic dynamic cards with OAuth auto-refresh).
- VS Code extension for viewing quotas inside the editor.
- Supports multi-account tracking for Codex, MiniMax, and Cursor.
- API Integrations allow ingesting local telemetry from custom API-driven workflows.
- Zero telemetry; all data stored locally in SQLite.
Use cases
- Monitor AI API quotas across multiple providers in real time to avoid throttling or budget overruns.
- Track historical usage trends and reset cycles for better capacity planning.
- Manage multiple accounts for Codex, MiniMax, or Cursor from a single dashboard.
- Integrate custom API workflows to centralize token and spending telemetry.
- Use the VS Code extension to check quotas without leaving the editor.
Getting started
One-line install (macOS & Linux): bash curl -fsSL https://raw.githubusercontent.com/onllm-dev/onwatch/main/install.sh | bash One-line install (Windows PowerShell): powershell irm https://raw.githubusercontent.com/onllm-dev/onwatch/main/install.ps1 | iex After installation, edit ~/.onwatch/.env (or .env in the project directory) with at least one provider API key. Then run: bash onwatch # start in background onwatch --debug # foreground mode onwatch stop # stop the instance onwatch status # check status Open http://localhost:9211 and log in with the credentials from .env.
License and pricing
GPL-3.0 open source, free.
Based on the project's public README and repository metadata.
