ncoder 0.1.0

Jupyter notebook plugin to generate code with AI

💫 ncoder

ncoder is an open-source AI coding agent that integrates with Jupyter Notebooks. This project uses the OpenAI API client to connect to any OpenAI-compatible endpoint and enable collaborative coding with AI.

ncoder provides a base Docker image that supports coding with OpenCode in server mode, a quantized Qwen3-Coder 30B model for lightweight local inference and/or any other txtai process.

Quickstart

Install the Jupyter Notebook extension on your local machine.

pip install ncoder

ncoder provides a default server as a Docker image. Run one of the following.

# DEFAULT: Run with opencode backend, sends data to `opencode serve` endpoint
docker run -p 8000:8000 --gpus all --rm -it neuml/ncoder-server

# ALTERNATIVE 1: Run with qwen3-coder, keeps all data local
docker run -p 8000:8000 -e CONFIG=qwen3-coder.yml -gpus all --rm -it neuml/ncoder-server

# ALTERNATIVE 2: Run with a custom txtai workflow
docker run -p 8000:8000 -v config:/config -e CONFIG=/config/config.yml --gpus all --rm -it neuml/ncoder-server

Jupyter Notebooks can be created in Visual Studio Code or your preferred notebook platform. Add the following two sections to test.

# Load ncoder extension
%load_ext ncoder

# Test it out
%ncoder Write a Python Hello World Example

An example notebook is also available.

If you already have a LLM API you'd like to integrate with, it's simply a matter of setting the correct environment variables.

%env OPENAI_BASE_URL=LLM API URL (e.g. https://api.openai.com/v1)
%env OPENAI_API_KEY=api-key
%env API_MODEL=gpt-5.2
%load_ext ncoder

Demo

The short video clip below gives a brief overview on how to use ncoder.