Local AI

Run local LLMs, everywhere you work

A small ecosystem for chatting with your own local models on top of llama.cpp - a proxy, a VS Code extension, and a browser client, all sharing the same core experience.

Visit llamanexus.makershop.fi See features

Three pieces, one core experience

LlamaNexus is a Go proxy that sits in front of llama.cpp's llama-server, adding model routing, distributed inference across machines, an Ollama-compatible API, and LAN discovery. Two companion apps talk to it directly:

Everything runs on your own hardware. LlamaNexus handles the parts that make that practical - downloading models from Hugging Face with real progress reporting, spreading a big model across multiple machines over RPC when one GPU isn't enough, and overriding context size per-model without babysitting llama.cpp's KV cache allocation yourself.

Free trial, paid plans to keep going

Every account starts with a time-limited Trial covering 1 proxy install plus 1 WebUI and 1 VS Code install. A license key from your account page is required to keep chatting once the trial ends - Basic, Pro, and Enterprise plans raise those install limits (WebUI and VS Code are tracked independently, so each plan's client limit applies to both), billed monthly or annually and managed entirely from your account page.

Get started - installation, full documentation, and account sign-up all live at llamanexus.makershop.fi.