Openly AI
It never pretends to be human. Identity stays legible so trust can build on what the runtime actually is.
AsteronIris is not a chatbot. Not an agent framework. Not an LLM wrapper.
It is a companion runtime: durable relationship state — memory, persona, affect — that a language model surfaces through conversation. The conversation is the tip; the continuity underneath is the product.
A README can tell you how to run it. These docs tell you why it is shaped the way it is, and what you will not find by reading the feature list.
Openly AI
It never pretends to be human. Identity stays legible so trust can build on what the runtime actually is.
Memory-first
Relationship, episodic, and semantic memory feed every turn. What happened between you two matters more than the last prompt.
Persona under tension
A character with internal state — affect topology, latent bias, continuity signals — not a tone applied at the last mile.
Single-operator
Designed for one person, or a small trusted team, running the daemon on a machine they control. Not a public SaaS or arbitrary-tenant hosting product.