AI alignment framework. Nine interdependent theories — CASCADE, AURA, LAMAGUE and six more — each mathematically proven, each converging on the same constants. Banach fixed points. Constitutional invariants. MCP extension for Claude Code. Built by one self-taught researcher. Open. Testable. Human.
npx skills add Lycheetah/Lycheetah-FrameworkAI alignment framework. Nine interdependent theories — CASCADE, AURA, LAMAGUE and six more — each mathematically proven, each converging on the same constants. Banach fixed points. Constitutional invariants. MCP extension for Claude Code. Built by one self-taught researcher. Open. Testable. Human.
Provides implementation patterns for Clean Architecture, Hexagonal Architecture (Ports & Adapters), and Domain-Driven Design in Java 21+ Spring Boot 3.5+ applications. Use when structuring layered architectures, separating domain logic from frameworks, implementing ports and adapters, creating entities/value objects/aggregates, or refactoring monolithic codebases for testability and maintainability.
An operating system for your Claude Code skills, agents & MCPs — organize everything into auto-routing orchestras.
LLM agent skills for software architecture analysis and review. This repository equips AI agents with reusable capabilities to evaluate system design, review architecture decisions, identify risks, analyze trade-offs, and recommend improvements for scalable, reliable, and maintainable systems.
«Второй мозг» (Karpathy-style) graph-canonical язык для детерминированных multi-step AI-workflow
Codex skill for academic slides, posters, proofsheets, and architecture diagrams via GPT Image 2
Recover Claude Code and reset Python state for a clean CLI port with preserved module logic and no UI layer