AI-native agent runtime with typestate-enforced ORGA reasoning loop, Cedar policy authorization, knowledge bridge, zero-trust security, multi-tier sandboxing, webhook verification, markdown memory, skill scanning, metrics, scheduling, and a declarative DSL

原生AI代理运行时，采用类型状态强制的ORGA推理循环、Cedar策略授权、知识桥接、零信任安全、多层沙箱、Webhook验证、Markdown内存、技能扫描、指标监控、调度功能及声明式DSL