A full AI stack running on my own machine. No cloud, no account, no data leaving the house — and it knows me.
A little server on the GPU machine. Any phone or laptop on the same wifi opens one address and chats to the local model. No install their end.
Download server ↓Bakes my identity, tone and slang into a custom model called killa — so it knows it's local and knows me. No more "I'm a cloud service".
Inline coding assistant. Sidebar chat + right-click Explain / Refactor / Comment / Fix on any selection — all on the local model.
Download extension ↓Just the chat page on its own — open it on the GPU machine and go. The simplest way to talk to your local Llama.
Open chat box →start-here.ps1 on the GPU
machine, and it prints an address like http://192.168.1.50:8080. Open that on any
device on the same wifi — that's the one to show people.