LlamaNexus for VS Code

Chat with, explain, and edit code using your local LlamaNexus proxy directly inside VS Code - no Open WebUI needed.

It talks to LlamaNexus's OpenAI-compatible endpoints:

• POST {baseUrl}/openai/v1/chat/completions (streaming SSE, with tool-calling support)
• GET {baseUrl}/openai/v1/models (includes each model's real context size and whether it's currently loaded)
• GET {baseUrl}/status (connection check, plus current RPC worker mode/roster)
• POST {baseUrl}/api/set-ctx-size, /api/eject-model, /api/remove-model
• POST {baseUrl}/api/rpc/mode, /api/rpc/workers, /api/rpc/workers/remove
• POST {baseUrl}/ollama/api/pull (download a not-yet-present model, streaming progress)

Requirements

Run a LlamaNexus proxy first - it ships only as a Docker image, see Docker setup for the full Compose example. Minimally:

docker run -d --network host makershop/llamanexus:cuda-13.0.0-latest \
  serve --port 11434 --llamaport 8080 -- --jinja

--jinja is recommended if you want tool calling to work reliably - without it, llama-server falls back to minimal built-in template handling instead of the model's real chat template, which for some models (e.g. Qwen3-Coder) means tool calls can leak out as literal text instead of structured JSON on later turns in a conversation.

See Installation to build/install the extension, Features for the full feature set, and Settings for configuration.

In this section