AIOpenCode
6 min read
Deploying Qwen3-Coder-30B-A3B on 8GB GPU with Docker
A 30B model on an 8GB GPU sounds impossible, but quantization and llama.cpp make it work. This guide shows how to run it with Docker and use it in OpenCode.
Automation & Tools
A technical journey through Playwright snippets, AI-driven testing, and the automation playbooks of everyday QA engineering.
Latest Insights
Showing 4 Total Articles
PlaywrightTest Automation
19 min read
From WSL2 to Self-Healing Tests: A Local LLM Pipeline with llama.cpp and Playwright
Private, self-healing Playwright test loop on WSL2 using llama.cpp via Docker, GPU acceleration, and OpenCode agents
AutomationOpenCode
28 min read
OpenCode Agents & Skills: Build Your Own AI Dev Team - Without the HR Headaches
Build a multi-agent AI dev team in OpenCode — with agents, skills, Playwright integration, and every config mistake I made so you don't have to.
PlaywrightCI/CD
7 min read
From 45 Minutes to 8: Dockerizing and Parallelizing Playwright CI/CD Pipelines
A practical guide to transforming sluggish, flaky Playwright test suites into fast, reliable CI/CD pipelines using Docker containers and intelligent parallelization strategies.