Hybrid Cloud AI Chat

Name: Ollama Integration
Author: Earl McGowen

Private LLM inference from a home GPU, securely proxied through the cloud.

Built by Earl McGowen

桜

🔧

Frontend SvelteKit on Hostinger VPS

Proxy Flask + Nginx with Auth

Inference Ollama on Home GPU

Security API Key + Concurrency Lock

🌸

Choose an example or type your own message below.

Press Enter to send, Shift+Enter for new line