llama-brain local model server
A small AI model that runs on my laptop for voice features.
built Oct 2026
Running a team of AI agents
how it works
Qwen3.5-4B GGUF on llama.cpp Metal via launchd.
Automation: Something that runs on a schedule by itself.
The code for this one lives in a private repo. This page explains the idea so you can build your own.