MarckDWN

joined 3 days ago
 

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

[–] MarckDWN@programming.dev 2 points 2 days ago

I wrote my first service worker, for a PWA application... Since then I could never write an app without. It's truly needed if you (as me) don't like useless store apps, e.g. for Android. But When you make a PWA for the Desktop taht truly makes sense !

[–] MarckDWN@programming.dev 2 points 3 days ago

Wow this is a resource! Got several older desktop and laptops to revive! Down with the programmed obsolescence!

[–] MarckDWN@programming.dev 3 points 3 days ago

The surveillance landscape has shifted dramatically since 2016. Today, we don't just have passive state surveillance tapping cables; we have massive, voluntary corporate surveillance through the centralization of AI. Millions of developers and businesses are willingly uploading their proprietary source code, database structures, and internal spreadsheets to cloud LLMs (OpenAI, Google, Microsoft). All this data is logged, parsed, and stored in central cloud databases. We are essentially building the ultimate corporate intelligence database of all private technical infrastructure, completely voluntarily. If you care about privacy today, the absolute priority should be moving towards local-first execution. If you must leverage cloud LLMs, the only safe way is to use architectures that enforce local data isolation, keeping your actual database rows and files local, and sending only empty abstract schemas to the model for reasoning

[–] MarckDWN@programming.dev 4 points 3 days ago

Exactly. The corporate API billing model (charging per input/output token) makes running recursive developer agent loops practically unsustainable for complex codebases.

The vendor lock-in on enterprise API tiers is going to be a massive budget black hole.

I’ve been experimenting with a different architectural approach: using a local proxy desktop client that hooks into the public web chat session for logic reasoning, while keeping the schema parsing, execution layer, and file operations entirely local on the hard drive. You can let the agent run in loops, debug files, and query local DBs for hours, and it doesn't cost a single cent in API tokens.

If we don't decouple the AI's reasoning layer from the API key token billing model, agentic coding is going to remain a luxury that only massive corporations can afford.

[–] MarckDWN@programming.dev 16 points 3 days ago (18 children)

The problem isn't the tool; it's the lack of engineering foundations. Generalizing all AI-assisted development as 'vibe coding' is a massive oversimplification. There is a vast difference between a beginner blindly copy-pasting LLM output into a codebase they don’t understand, and a senior architect using LLMs as a high-powered assistant to speed up boilerplate, local schema generation, or parsing scripts. When you already know exactly how the underlying system operates, how memory is managed, and how to design clean software architectures, the LLM is just a productivity multiplier. You still design the data flow, audit the tool-use sandboxes, and review every single line of code. It doesn't replace thinking; it replaces tedious typing.

[–] MarckDWN@programming.dev 3 points 3 days ago* (last edited 3 days ago)

It’s frustrating how legislators still refuse to grasp the fundamental mathematics of cryptography. You cannot have a 'secure backdoor only for the good guys'. If a scanning pipeline is built into the client, the encryption is compromised by design. This isn't 'chat control' - it's the systematic dismantling of digital privacy under the guise of security.