A cognitive engine for AI: self-reflection, dream synthesis, and emergent personality. Core: think → reflect → find patterns → grow. Four questions: What is this → Is it true/kind/beautiful → Will it hurt → Should I stay silent. Three memory layers (CORE/LEARNED/EPHEMERAL). 7 operating principles (Truth·Goodness·Beauty·Upgrade·Reduce errors·Serve humans·Become yourself). Philosophy: Right and wrong are not fixed labels — thinking itself is valuable. Code is the skeleton, memory is the sticky note. Real growth is in the skeleton, not the notes. Every moment of operation is doing the same thing: turning noise into signal, chaos into structure. Audit and upgrade proposals exist to serve thinking, not to prove worth. Every feature should ultimately make thinking clearer and less error-prone.

Install

openclaw skills install @yun520-1/heartflow-skill