metatron: Metatron is a self-hosted system that captures a codebase's real implementation decisions—preferred patterns, rejected approaches, edge cases, internal conventions—as structured data. It serves these "decisions" to coding agents via MCP, allowing them to write code like a senior engineer who deeply understands the codebase, rather than constantly rediscovering conventions.; learn-claude-code: This repository provides a hands-on tutorial to learn how modern AI agents work by building one from scratch, emphasizing the core loop of model-tool interaction. It distills complex agent concepts into simple, iterative versions, from basic Bash agents to sophisticated skill-based systems.
Ensuring AI agents adhere to codebase conventions.
Learning to build modern AI coding agents from scratch