davila7/gemini-cli-templates

Gemini CLI Analytics Dashboard

This project provides an advanced analytics dashboard for the Gemini CLI. It allows you to monitor real-time metrics, track token usage, and visualize OpenTelemetry data locally.

Features

• Real-time Metrics: Track sessions, tool usage, token consumption, and API calls.
• Interactive Charts: Visualize token usage, session activity, and API response times.
• Data Filtering: Analyze data by date range (last 7, 30, 90 days, or custom).
• Log Viewer: Inspect detailed, paginated logs for metrics and traces.
• Data Export: Download analytics data as a JSON file.

How It Works

This dashboard leverages the local OpenTelemetry data generated by the Gemini CLI.

1. Telemetry Enabled: When you run gemini with the --telemetry -- --target=local flag, it activates OpenTelemetry instrumentation.
2. Local Collector: The CLI sends telemetry data (metrics and traces) to a local OpenTelemetry Collector running in the background.
3. Log Storage: The collector writes this data to a log file at ~/.gemini/tmp/<session-id>/otel/collector.log.
4. Express Backend: The dashboard's Node.js/Express server reads and parses this log file to extract structured metrics.
5. Jaeger Integration: For distributed tracing, the dashboard proxies requests to a local Jaeger instance (run via Docker), allowing you to visualize request flows.
6. Frontend UI: A vanilla JavaScript frontend fetches the processed data from the Express server and renders it using interactive charts and tables.

Technology Stack

• Backend: Node.js, Express
• Frontend: HTML, CSS, Vanilla JavaScript
• Charting: Chart.js
• Telemetry: OpenTelemetry, Jaeger

Quick Start

Prerequisites

• Gemini CLI installed
• Node.js 18+
• Docker (for the Jaeger telemetry backend)

1. Install Gemini CLI

npm install -g @google/gemini-cli

2. Run Gemini with Telemetry

For the dashboard to receive data, you need to run your gemini commands with the --telemetry -- --target=local flag. This sends telemetry data to a local collector.

gemini --telemetry -- --target=local

3. Launch the Analytics Dashboard

You can launch the dashboard using npx (recommended) or by cloning the repository locally.

Option A: Using npx

This command runs the latest version of the dashboard without cloning the repository.

npx gemini-cli-templates@latest --analytics

Option B: Clone and run locally

git clone https://github.com/davila7/gemini-cli-templates.git
cd gemini-cli-templates
npm install
npm start

4. View Analytics

Once the dashboard is running, open http://localhost:3337 in your browser to see the analytics interface.

Contributing

Contributions are welcome! Please follow these steps:

1. Fork the repository.
2. Create a new feature branch (git checkout -b feature/your-feature).
3. Commit your changes (git commit -m 'Add your feature').
4. Push to the branch (git push origin feature/your-feature).
5. Open a Pull Request.

License

This project is licensed under the MIT License. See the LICENSE file for details.