Building a local AI agent in Workshop on Ubuntu

Build a fully local AI coding agent on Ubuntu using Canonical Workshop and the Qwen3-Coder Inference Snap.

In this step-by-step demo, you'll set up an isolated development environment, connect your coding agent to a locally hosted LLM, and run coding tasks without an internet connection. Follow along to recreate the setup on your own machine, using CPU or GPU inference.

Resources:
› Download Ubuntu: https://ubuntu.com/download
› Install Canonical Workshop: https://snapcraft.io/workshop
› Install Qwen3-Coder Inference Snap: https://snapcraft.io/qwen3-coder
› Configuration files: https://github.com/canonical/local-ai-agent-pi-workshop

Chapters:

00:00 Introduction and sandbox demo

00:45 System architecture overview

01:26 Installing the Qwen3-Coder inference snap

05:04 Installing Workshop

05:32 Defining the workshop

06:40 Launching the workshop

08:06 Declaring the tunnel

11:06 Configuring the local model for Pi

13:43 Putting everything together

14:46 Closing remarks

#Canonical #Ubuntu #Workshop #Developer