A hands-on engineering blog. Every post covers a complete, working system - the decisions behind it, the code that runs it, and the failure modes that shaped it.
⚡ Severing the API Cord
llama.cpp · Gemma-4 26B · OpenCode · Apple Metal · ~10 min read
I compiled llama.cpp with Metal GPU acceleration on an M1 Mac, loaded Google’s Gemma-4 26B via Unsloth’s quantization, and wired it to OpenCode for a fully agentic, offline coding workflow. Total API cost: $0. Data sent to the cloud: 0 bytes.
🤖 InfraSquad - Multi-Agent AWS Infrastructure
LangGraph · Terraform · AWS · Security Automation · ~15 min read
Four specialized AI agents collaborate in a cyclic LangGraph state machine to architect, write Terraform, audit security with remediation loops, and render architecture diagrams - from a single plain-English description.