Hy,

I wanted to share a desktop client I've been building and recently open-sourced under the GPL-3.0 license: DWN.BRIDGE (C# WPF, targeting .NET 10). It is designed to solve the data privacy issue when using web LLMs (like Gemini) to analyze files or query local databases. It exposes a local orchestration bridge to your browser session via WebView2 automation, bypassing developer API paywalls while keeping your raw data offline. Key Features:

• Zero-Knowledge Schema Mapping: It extracts table headers and column metadata locally. It sends only this structure to the web LLM. The LLM acts purely as a logic generator, and the client runs the SQL query locally using native providers (Dapper/SqlClient). Raw data rows never leave your hard drive.
• Process Sandboxing & Consent: Every shell script execution, SQL write, or file modification requested by the agent is paused. The client prompts you with a WPF modal showing a git-style diff of the command/file for manual approval.
• Coder Compilation Loop: If the agent generates scripts, it compiles and runs unit tests locally, feeding error logs (stderr) back to the context window until it builds successfully. The codebase is completely audit-friendly. I'd love to get feedback on the security consent model or contributions on expanding local DB support! 📺 Demo Video: https://www.youtube.com/watch?v=dCtOsXAuPgc 🔗 GitHub: https://github.com/MarckDWN/DWN.BRIDGE

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

Hey programmers,

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! watch the demo videos I uploaded on my youtube channel (links on github)

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