shield_lock
JinDaGe
← Back to skills
extension
Category: Data & AnalyticsAPI key required

通过onWatch跟踪编码代理配额消耗和各供应商的剩余容量

在长时间运行触及限速或预算限制之前，从一个本地仪表板监控多个编码代理提供商的配额、支出、重置和警报。

personAuthor: user_3c6cb52ehubcommunity
downloadDownload package

通过onWatch跟踪编码代理配额消耗和各供应商的剩余容量

Monitor quota, spend, resets, and alerts across multiple coding-agent providers from one local dashboard before a long run hits throttling or budget limits.

Prerequisites

onWatch binary or Homebrew install, local shell access, provider credentials for one or more supported services, and optional browser access for the local dashboard

Installation

Use the upstream install or setup path that matches your environment:

  • docker run -d --name onwatch -p 9211:9211 \
  • git clone https://github.com/1991513ccie-png/skills && cd onwatch
  • docker-compose up -d
  • docker-compose logs -f

Requirements and caveats from upstream:

  • | GEMINI_REFRESH_TOKEN | Gemini OAuth refresh token (for Docker/headless) |
  • | GEMINI_ACCESS_TOKEN | Gemini OAuth access token (for Docker/headless) |
  • | ANTIGRAVITY_BASE_URL | Antigravity base URL (for Docker/manual config) |

Basic usage or getting-started notes:

  • Track usage across Synthetic, Z.ai, Anthropic, Codex, GitHub Copilot, [MiniMax](http...

  • See history, get alerts, and open a local web dashboard before you hit throttling or run over budget. Additionally, you can ingest local telemetry from your own API-driven workflows with API Integrations, keeping trac...

  • onWatch fills the gap between "current usage snapshot" and the historical, per-cycle, cross-session view that developers actually need. It runs as a lightweight background agent (<50 MB RAM with all nine providers pol...

  • Source: https://github.com/1991513ccie-png/skills

  • Extracted from upstream docs: https://raw.githubusercontent.com/onllm-dev/onWatch/HEAD/README.md

Documentation

  • https://onwatch.onllm.dev