LlamaNexus documentation

The LlamaNexus ecosystem is three products that share one core chat experience over your own local models. Pick one below to get started.

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

The same chat experience as a VS Code extension, no browser tab needed.

A standalone, smooth browser chat client for a LlamaNexus proxy.