Memory & continuity
Persistent autobiographical history and provenance are treated as part of the system, not merely text placed in a prompt.
Brain Architecture for AI Systems
LUNA Longitudinal Unified Narrative Architecture
Cognitive infrastructure for artificial systems that develop through memory, experience, continuity, and time.
THE CENTRAL QUESTION
What changes when an AI system can accumulate a causal history?
Most AI systems are assembled from the information available to them now. LUNA investigates what changes when the system interpreting the present has itself been altered by what happened before.
Conventional framing
Give the model more context. Store information so it can be retrieved later.
→
LUNA framing
Give the persistent system a history. Let experience change the conditions of later cognition.
AN ARCHITECTURE FOR A MIND
Not another agent loop.
LUNA surrounds interchangeable inference models with longitudinal cognitive infrastructure. The research is about how multiple systems interact across time, not how to make one prompt imitate a persistent mind.
Associative cognition
LUNA explores cognition in which active memories and newly formed cognitive products can make other relevant material available.
Development
The research distinguishes remembering an experience from being structurally changed by it over time.
Perception
The architecture is designed for persistent environmental models in which stable input can become computationally quiet.
Motivation & choice
Requests, goals, expectations, preferences, and commitments can become reasons that participate in action selection rather than direct triggers.
ChronoForge
Controlled longitudinal simulated environments are designed to study development, branching histories, and comparative AI behavior.
Research posture Concepts and observations are public where useful. Reproducibility-critical implementation details remain protected.
FIRST PUBLIC RESEARCH NOTE
Remembering something is not the same as being changed by it.
When Memory Is Not Enough: Can an AI Be Changed by Experience?
An early interaction produced a useful accidental control condition: autobiographical material was available to the system, but availability alone did not make it part of creative output. The observation exposed a larger research problem — the difference between storage, retrieval, causal use, and developmental integration.
Read the research note →OPEN RESEARCH · PROTECTED IMPLEMENTATION
Follow the questions, the architecture, and the evidence.
LUNA publishes high-level architecture, research questions, selected observations, experimental designs, and results where they can advance understanding without turning the public site into a reconstruction manual.