onllm-dev/onWatch — Track AI API quotas across Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigra…

Description and use

**Project Summary:**

onWatch is an open-source project that tracks AI API quotas across multiple platforms, including Synthetic, Z.ai, Anthropic, Codex, GitHub Copilot, and Antigravity, in real-time. This lightweight background daemon utilizes SQLite storage and a Material Design 3 dashboard, ensuring zero telemetry. By making internal knowledge searchable and usable by assistants, onWatch aims to improve search over documents and ground assistant answers.

**Value Proposition:**

The primary value proposition of onWatch lies in its ability to make internal knowledge searchable and usable by assistants. This is particularly useful for organizations seeking to index knowledge bases, improve search functionality, and ground assistant answers. By utilizing onWatch, businesses can leverage their existing knowledge bases and improve the accuracy and reliability of their AI-powered assistants.

**Practical Adoption Path:**

The practical adoption path for onWatch involves the following steps:

1. **Evaluation**: Evaluate the project's implementation signals, such as API/SDK/CLI, language metadata, or focused topics, to ensure it meets your specific needs.
2. **Integration**: Integrate onWatch with your existing systems and infrastructure, taking into account any necessary configuration or setup.
3. **Testing**: Test onWatch in a controlled environment to ensure it meets your performance and functionality requirements.

Problem

onllm-dev/onWatch helps make internal knowledge searchable and usable by assistants.

Outcome

High for an OSS candidate: recent activity, adoption, and ecosystem signals are strong enough for a serious pilot.

Workflow

• index knowledge bases
• improve search over documents
• ground assistant answers

Evidence

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.

Source