Sniffly: Claude Code Analytics Dashboard for Usage and Error Analysis

Summary

Sniffly is an open-source Python project that provides a comprehensive dashboard for analyzing Claude Code logs. It helps users understand their usage patterns, identify common errors, and review message history to improve their interaction with Claude Code. The tool runs locally, ensuring privacy, and offers a unique feature for sharing project statistics.

Use at your own risk

OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.

Introduction

Sniffly is an open-source Python project designed to provide a comprehensive analytics dashboard for Claude Code logs. It empowers developers to gain deeper insights into their interactions with Claude Code, helping them understand usage patterns, identify common errors, and review their message history. By running entirely on your local machine, Sniffly ensures complete privacy while offering powerful analytical capabilities and a unique feature for sharing project statistics with colleagues.

Installation

Sniffly requires Python 3.10+ to run. Choose your preferred installation method below:

With UV (recommended)

Ensure you have uv installed from https://github.com/astral-sh/uv.

One-time execution (no installation needed):

uvx sniffly@latest init

Install the package:

uv tool install sniffly@latest
sniffly init

With pip

pip install sniffly
sniffly init

From source

git clone https://github.com/chiphuyen/sniffly.git
cd sniffly
pip install -e .
sniffly init

After running sniffly init, access your dashboard in your browser at http://localhost:8081 (or your chosen host/port). If running on a remote server, use port forwarding to access it locally.

Examples

Sniffly offers several key features to help you analyze your Claude Code usage:

Understanding Usage Patterns: Visualize your interaction frequency and patterns with Claude Code to optimize your workflow.
Error Breakdown: Pinpoint where Claude Code makes mistakes, allowing you to learn from them and refine your prompts or coding approach.
Message History Analysis: Review all your instructions and Claude Code's responses, providing a clear walkthrough of your development process.
Configuration: Customize Sniffly's behavior, such as changing the server port or disabling auto-opening the browser. For example:
```
sniffly config set port 8090
sniffly config set auto_browser false
sniffly config show
```
Sharing Your Dashboard: Easily create shareable links for your project's stats and instructions. Click the "Share" button in your dashboard, choose privacy options (Private, Public, Include Commands), and share the generated link with coworkers.

Why Use Sniffly?

Improve AI Interaction: Gain actionable insights into your Claude Code usage, helping you write better prompts and avoid common pitfalls.
Complete Privacy: All data processing occurs locally on your machine, with no telemetry. Your conversations never leave your computer, ensuring your privacy.
Shareable Insights: Facilitate collaboration by easily sharing project statistics and command histories with your team.
Open Source and Extensible: Being open source, Sniffly offers transparency and the potential for community contributions and customization.