GraphCanon updated 2w · GitHub synced 2w
Decision brief
onWatch monitors AI API quotas in real time for multiple services including Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigravity. It is a lightweight daemon with zero telemetry.
Good fit when
- Use onWatch if you need to track quota across a broad range of AI APIs, especially those it directly supports like Anthropic Claude Code and GitHub Copilot.
- Choose it for its low memory footprint under 50MB when monitoring multiple services in real time, without sending any user data away.
Avoid when
- Avoid onWatch if your API providers are not supported or if you require a more extensive set of features beyond quota tracking.
- If file permissions and bind mounts for SQLite storage pose operational challenges, consider alternatives with simpler setup processes.
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (1d since push)
- As of 2w
- Provenance
- Not a fork · Organization account
- As of 2w
- Security (OSV)
- 27 low (27 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
go get github.com/onllm-dev/onWatchHow it fits your stack(1)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
onWatch is a lightweight daemon that monitors and tracks usage quotas for various AI APIs, including Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigravity
Capability facts
- Deploy
- Self-host
Source: dockerfile:Dockerfile · Aug 2, 2026
- Docker
- Dockerfile present
Source: dockerfile:Dockerfile · Aug 2, 2026
- Languages
- go
Source: github.language · Aug 2, 2026
Categories
Tags
README
Manual Installation
Download binaries from the Releases page. Binaries are available for macOS (ARM64, AMD64), Linux (AMD64, ARM64), and Windows (AMD64).
Or build from source (requires Go 1.25+):
git clone https://github.com/onllm-dev/onwatch.git && cd onwatch
cp .env.example .env # then add your API keys
./app.sh --build && ./onwatch --debug # or: make build && ./onwatch --debug
Or use Docker (requires Docker or Docker Compose):
cp .env.docker.example .env # add your API keys
docker-compose up -d
Or via app.sh:
./app.sh --docker --run
The Docker image uses a distroless base (~10-12 MB) and runs as non-root. An Alpine variant with shell access is also available (ghcr.io/onllm-dev/onwatch:alpine). Data persists via volume mount at /data. Logs go to stdout (docker logs -f onwatch). See Docker Deployment for details.
How do I monitor Z.ai (GLM Coding Plan) API quota?
Set ZAI_API_KEY in your .env. onWatch polls the Z.ai /monitor/usage/quota/limit endpoint and tracks token limits, time limits, and tool call quotas. All providers can run simultaneously.
How do I track my MiniMax Coding Plan usage?
Set MINIMAX_API_KEY in your .env with your MiniMax Coding Plan API key. Get your key from the MiniMax Console. onWatch tracks the shared quota pool across all MiniMax models (M2, M2.1, M2.5) with 5-hour rolling window reset cycles. To track multiple MiniMax subscriptions, add additional accounts via the dashboard Settings > MiniMax > Add Account. Each account polls independently with its own API key and region. Full walkthrough: MiniMax Setup Guide.
Docker Deployment
The container auto-detects the Docker environment and runs in foreground mode with stdout logging.
[!NOTE] onWatch provides Docker support with a distroless runtime image (~10-12 MB) and an Alpine variant (~15 MB) with shell access. You will almost certainly need to account for file permissions when using bind mounts for the SQLite database, as the container runs as non-root (UID 65532). See Storage below for details.
Quick Start
Using pre-built images from GitHub Container Registry:
Multi-arch images (linux/amd64, linux/arm64) are automatically built and published on each release:
---
## License
GNU General Public License v3.0. See [LICENSE](LICENSE).
---
For agents
This page has a .md twin and JSON over the API.