This looks promising. Would love to hear how it compares to existing solutions in real-world use.

Interesting approach. Thanks for sharing — curious to see how this evolves and what problems it solves better than existing tools.

I like that you’ve added secret detection and multi-provider support — that’s something most LLM commit tools miss. Have you benchmarked latency differences between local models (like Ollama) and OpenAI/Anthropic? Would be interesting to see a speed comparison.