Run local LLMs, everywhere you work

LlamaNexus is 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.

A smart proxy for llama.cpp

A Go proxy that sits in front of llama.cpp's llama-server, adding model routing, RPC-distributed inference, an Ollama-compatible API, and LAN discovery.

View docs →VS Code

LlamaNexus for VS Code

Chat with your local models, without leaving the editor

A VS Code extension bringing the full LlamaNexus chat experience - sessions, tool calling, Plan Mode, agent delegation - directly into the editor.

View docs →WebUI

LlamaNexus WebUI

A smooth browser chat client

A standalone browser chat client for a LlamaNexus proxy - the same core experience as the VS Code extension, as a normal web app instead.

View docs →