白箱AGI架构探索：元认知（自我认知循环）、持续学习（知识飞轮）、世界模型（条件空间+语义时空图）、自我改进（自举纪律）、零LLM白箱管线与可审计信任护栏。

Spec-driven development framework — AI agents that think before they type

The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.