I built an open-source, zero-telemetry local AI proxy daemon for absolute data sovereignty

A developer has open-sourced the Garza Global Graviton (GGG) Sovereign Edge Daemon, a self-contained local background daemon that runs an OpenAI-compatible loopback proxy endpoint at http://127.0.0.1:11834. The project claims zero telemetry and no cloud dependencies by construction, using HMAC-SHA256 response branding and a metadata pacer, and can connect to tools such as VS Code (Continue), Open WebUI, LM Studio, and Jan. It ships with plain-English setup guidance aimed at letting non-technical users secure local AI pipelines.

Hey everyone 👋 Like many developers, I love experimenting with local AI and custom workflows, but I got tired of worrying about data leaks, cloud telemetry, and being locked into a single AI app or vendor ecosystem. So, I built and open-sourced the Garza Global Graviton GGG Sovereign Edge Daemon — a single, self-contained background daemon designed for absolute data sovereignty. What it does GGG runs locally on your machine as an OpenAI-compatible loopback proxying endpoint http://127.0.0.1:11834 . - Zero Telemetry / Air-Gapped: No accounts, no cloud dependencies, and zero tracking code by construction. Your prompts, history, and context vaults never leave your hardware. - Sovereign Math Framework: Features a metadata pacer and HMAC-SHA256 cryptographic response branding to ensure data integrity. - Bring Your Own AI BYOAI : Because it speaks a standard API shape, you can hook it up to any compatible tool—like VS Code Continue , Open WebUI , LM Studio , or Jan —and your data stays portable. - Zero-Code Quick Start: It includes plain-English guidance and copy-pasteable setup prompts so non-technical users can secure their local AI pipelines in minutes. Quick Example Python SDK If you want to plug it into custom scripts or web UIs, it's just standard OpenAI configuration pointing to the local loopback: