I wanted to share a desktop client I've been building: DWN.BRIDGE (fully open-source C# WPF).

I love using AI for data analysis (like cleaning CSVs or querying databases), but there was no way I was going to upload my private/corporate files to cloud LLMs.

So I built a Zero-Knowledge local bridge:

• When you point the client to a local database (SQL Server, SQLite, Excel, CSV), the client extracts ONLY the table schemas/headers locally.
• It sends the schema metadata to the LLM (Gemini web UI) via a secure browser-automation bridge.
• The LLM writes the SQL query, and the client executes it locally on your computer. Your raw rows and records never leave your hard drive.
• All local file system access and system commands run locally and require explicit pop-up confirmation.

You can check out the source code or download the installer below. I'd love to get feedback on the local sandboxing model!

🔗 GitHub: https://github.com/MarckDWN/DWN.BRIDGE