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.; awesome-cursorrules: This repository offers a collection of .cursorrules configuration files designed to enhance the Cursor AI editor by defining custom rules for code generation. It allows developers to tailor the AI's behavior to specific project needs, promoting consistency, context awareness, and improved productivity across various tech stacks.
Ensuring AI agents adhere to codebase conventions.
Tailoring AI code generation for specific frontend frameworks like Next.js or Angular.