GraphCanon
Home/LLM Frameworks/onWatch
onWatch logo

onWatch

Enrichment pending
onllm-dev/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 dash

GitHub Website

GraphCanon updated today · GitHub synced today

673
Stars
51
Forks
11
Open issues
3
Watchers
3w
Last push
Go GPL-3.0Created Feb 6, 2026

Trust & integrity

Full report
Maintenance
Active (22d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Organization account
As of today · Source: github_public_v1
Security (OSV)
27 low (27 low)
As of today · Source: osv@v1

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

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.

Capability facts

Deploy
Self-host

Source: dockerfile:Dockerfile · Jul 11, 2026

Docker
Dockerfile present

Source: dockerfile:Dockerfile · Jul 11, 2026

Languages
go

Source: github.language · Jul 11, 2026

Categories

LLM FrameworksComputer VisionInference & Serving

Tags

ai-api-monitoringapi-monitoringcodexantigravityopenaiclaude codedeveloper-toolsgolang

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).

---