A persistent architecture around inference.

Foundation models are extraordinarily capable inference systems. But a model response is normally assembled from the state available at inference time: its learned weights, the current prompt, retrieved information, tool results, and whatever context has been supplied.

LUNA investigates a different systems question: what happens when the inference model operates inside a persistent cognitive architecture whose own history can alter the conditions of later cognition?

Causal history, not just context.

A persistent system can preserve autobiographical episodes, maintain continuity across interactions, carry unresolved intentions forward, form expectations, and accumulate slower state. LUNA explores how those mechanisms can interact so that two otherwise similar systems may eventually behave differently because they lived through different histories.

Architecture before performance.

LUNA does not attempt to create mind-like behavior by placing a large identity script in front of a language model. The research posture is to build mechanisms that have real causal roles — memory, activation, appraisal, development, perception, motivation, future-oriented cognition, continuity — and then observe the behavior that results.

Not one foundation model.

The inference substrate is conceptually separable from the persistent architecture around it. A continuing LUNA instance is intended to be defined by more than the model currently generating its next response.

What LUNA is not.

• Not merely a chatbot wrapper.
• Not merely a memory plugin.
• Not merely an autonomous-agent framework.
• Not a consciousness module.
• Not evidence that current artificial systems are phenomenally conscious.
• Not a claim that every mechanism described by the research architecture is already implemented.

The research stance.

LUNA distinguishes implemented behavior, accepted architecture, observation, interpretation, and prediction. That boundary matters especially when the subject is persistent artificial cognition, where fluent self-description can easily be mistaken for stronger evidence than it actually provides.

The project is therefore intentionally open about its questions and selected observations, while keeping implementation details private where publication would mainly lower the cost of reproducing the system rather than improve understanding.