Archives

`pk`, the TUI for creating "coding helpers" with very small local language models (<=`10b` parameters)

Build pk, a TUI for crafting coding helpers backed by very small local language models (<=10b parameters) for offline Rust work.

Running Mistral's Vibe CLI in an `sbx` sandbox

Run Mistral's Vibe coding agent CLI securely inside an sbx sandbox, with credential handling and network isolation.

Docker Agent meets Kronk safely with `sbx`

Run docker-agent against the Kronk local inference server, all wrapped safely inside an sbx sandbox with GGUF models.

Improving the Developer Experience with SBX Kits

Improve the developer experience with sbx kits: reusable sandbox customizations for Go, Node.js, and code-server extensions.

Giving capabilities to our mini `docker-agent` with "mini skills"

Give your mini docker-agent new capabilities with mini skills that fork context and delegate heavy lifting to scripts.

How to cook a little coding agent with Docker Model Runner and Docker Agent (and `sbx`)

Cook a little coding agent from a 4B model with docker-agent and sbx, constraining tools so small local LLMs stay reliable.

Embedding a Web IDE and Docker Agent into `sbx`, a fully secured sandbox

Embed a web IDE and docker-agent into an sbx sandbox with Docker Model Runner for a ready-to-use secure dev environment.

Building a form with 🫟 Pablo

Go further with Pablo by building a real form: multiple fields, buttons, layout, event handling, and saving to a file.

Pablo, a small Golang library to make your life easier with BubbleTea

Pablo is a small declarative TUI framework for Go, built on BubbleTea, bringing HTML-like component composition to the terminal.

Using `docker-agent` with Docker Model Runner and `sbx`

Run docker-agent fully secured inside an sbx sandbox while it talks to Docker Model Runner for local inference.

Hello Estrela ⭐️

Estrela is a Lua 5.4 interpreter written entirely in GoloScript, pushing the revived Golo language into real language implementation.

"Micro" Vibe Coding with Docker Agent and Qwen3 Coder 30b

Micro vibe coding: use skills and precise templates to get moderately complex code out of a local model like Qwen3 Coder 30b.

Building a News Roundup with Docker Agent, Docker Model Runner and `qwen3.5-4b`

Build a fully local IT news roundup agent with Docker Agent, Docker Model Runner, and a skill that queries the Brave Search API.

Docker Agent and Tiny Language Models: One Tool to Rule Them All

Do function calling with tiny language models by swapping complex tool schemas for one generic CLI-first tool in Docker Agent.

Quality and vibe coding: take back control of your project

Keep control of your vibe-coded projects with a structured methodology, quality gates, and continuous code analysis.

**`cagent`** with Tiny Language Models and Sub Agents

Build collaborative multi-agent teams with cagent sub-agents, tuning each one for reasoning or creativity.

Fine-tune a Tiny Language Model on Mac with DonkeyTune and use it with Docker Model Runner

Fine-tune a tiny language model on a Mac with DonkeyTune, then export to GGUF and run it with Docker Model Runner.

Using RAG as a NoSQL Database for More Accurate Answers

Rethink RAG as a structured NoSQL store with metadata to get more accurate answers from small local models.

**`cagent`** with Tiny Language Models and Tools

Add tools and toolsets to a cagent agent so small language models can do file operations and function calling.

**`cagent`** with Tiny Language Models and Skills: Introduction

Introduction to cagent with tiny language models and skills, teaching a small AI assistant domain-specific knowledge.