Prefrontal

A unified frontend for local + cloud AI models
Ollama OpenRouter llama.cpp

Overview

Prefrontal is a frontend interface that connects multiple AI backends including local inference (Ollama, llama.cpp) and cloud APIs (OpenRouter). It acts as a unified control layer for switching between models seamlessly.

Key Features

🚀 Multi-backend support
💻 Local model execution
🌐 Cloud API routing
⚡ Fast switching between models

Tech Stack

Built to interface with Ollama, OpenRouter, and llama.cpp. Designed as a modular frontend system for AI routing.

Links

View Source Code
Diagnostic Settings