Sniffly

Sniffly - Claude Code Analytics Dashboard

Analyze Claude Code logs to help you use Claude Code better.

Website | Quickstart | Features | Sharable dashboard

📊 Features
Understanding your usage patterns

Error breakdown
_See where Claude Code makes mistakes so that you avoid these mistakes._

Message history analysis
_Walk through all your instructions and share them with your coworkers if needed._

🚀 Quickstart
- Requirement: Python 3.10+

With UV (recommended)
Make sure you have uv installed! https://github.com/astral-sh/uv

After running sniffly init, access your dashboard on your browser at http://localhost:8081 (or whichever host/port you choose).

If you run Sniffly on a remote server, use port forwarding to open the browser on your local computer.

With pip

From source

🔧 Configuration

Common Settings

All Configuration Options

See full CLI Reference for all options and commands.

💡 Sharing Your Dashboard
You can create a link to share your project's stats and instructions with your coworkers.

1. Click the "📤 Share" button in your dashboard
2. Choose privacy options:
   - Private: Only people with the link can view
   - Public: Listed in the public gallery
   - Include Commands: Share your actual command text
3. Copy and share the generated link

🚨 Troubleshooting

Common Issues

Port already in use?

Browser doesn't open?

Configuration issues?

For more issues, see GitHub Issues.

🔐 Privacy

Sniffly runs entirely on your local machine:
- ✅ All data processing happens locally
- ✅ No telemetry
- ✅ Your conversations never leave your computer
- ✅ Shared dashboards are opt-in only

📄 License

MIT License - see LICENSE file.

🔗 Links

- Homepage: sniffly.dev
- Documentation: Full CLI Reference
- Issues: GitHub Issues