SAGE

A cognition kernel that wraps a frozen LLM in a persistent identity + trust + governance loop — testing whether capability comes from structure, not weights. Research-stage; honest about what's real vs mocked.

本页的项目背景与编辑内容均可免费阅读。原始 GitHub 仓库仍是最终依据；只有收藏或参与讨论时才需要登录。