Philippe discusses using small language models (LLMs) for coding tasks, particularly with a Golang project called Nova. He outlines techniques for improving model performance through tailored prompts and a method called Retrieval Augmented Generation (RAG).

This article explains how to set up OpenCode with Docker Model Runner for a private AI coding assistant. It covers configuration, model selection, and the benefits of maintaining control over data and costs. The guide also highlights coding-specific models that enhance development workflows.

Docker is introducing a new way to run coding agents in isolated environments using container-based sandboxes. This approach allows agents to access necessary resources without compromising the local system's safety, addressing security concerns as agents become more autonomous. The current experimental version supports Claude Code and Gemini CLI, with plans for broader agent compatibility.

The GitHub repository for CoJudge offers a self-contained, offline code judging tool for LeetCode-style problems, utilizing Docker for consistent execution across different machines. It supports multiple programming languages and features a user-friendly web interface built with SvelteKit, enabling users to add their own problems and track progress persistently. The project is open-source and licensed under the MIT license.