Sensei

Transforms engineering standards from passive documentation into an active mentor by intelligently injecting relevant portions of a 57-section rulebook based on file types and operations, maintaining session memory of architectural decisions, and providing validation tools for consistent code quality and architectural compliance across development teams.

Sensei transforms engineering standards documentation into an active development mentor by intelligently injecting relevant portions of a comprehensive 57-section rulebook based on file types, operations, and context. Built with FastMCP, it analyzes code patterns across 50+ file types to determine which engineering principles are most relevant, maintains session memory of architectural decisions and constraints, and provides validation tools against established standards. The implementation coordinates 64 specialized AI personas across 12 categories, offers tools for recording and validating agreed-upon patterns, and supports session collaboration through Architecture Decision Records (ADRs), making it valuable for maintaining code quality standards, ensuring architectural consistency across teams, and providing contextual engineering guidance during development.