Physical state
Weather, water, food, materials, distance, work, health, and time are explicit state variables.

Wega Labs · Persistent agent research
Eighteen artificial residents begin in a valley. They have private memories, relationships, needs, and commitments. The world continues to update while no observer is present.
Technical paper
Draft 0.3 · 10 sectionsFormal model, state integrity, agent decisions, identity experiments, validation, and current implementation.
System objective / 01
The simulation runs without continuous human input. Residents can work, communicate, form relationships, create institutions, migrate, reproduce, and die.
When an observer returns, the system reports what changed, which events caused it, and what information each resident had when they acted.

Research subject / 02
December studies whether an agent remains behaviorally distinct as its body state, memory, relationships, environment, and underlying model change.
Information available to the resident at a specific time.
Sourced experiences, testimony, beliefs, commitments, and retrieval errors.
Shared history, obligations, trust evidence, and social recognition.
A selected command under material, social, and informational constraints.
Initial scenario / 03
Weather, water, food, materials, distance, work, health, and time are explicit state variables.
Each resident has private observations, memory, relationships, needs, commitments, and available actions.
Every accepted action produces events that record causes, authorization, state changes, and random draws.

System architecture / 04
Visible state, body state, accessible records, and delivered messages
Sourced episodes, beliefs, relationships, commitments, and procedures
Schema, actor, intent, targets, parameters, and believed preconditions
Validation · state transition · scheduler · named randomness
Immutable events, causal parents, authorization, hashes, and replay
State projections, timelines, causal graphs, metrics, and branches
Only validated commands can change canonical state. Memory, narration, model output, and the observer interface have no direct write access.
Model constraints / 05
Each requirement maps to state variables, transition rules, observable evidence, and tests.
Food, materials, tools, time, and labor cannot be created by model output.
A resident occupies one location. Travel, work, care, and communication require time.
Agents act on observations, testimony, beliefs, and memory rather than hidden world state.
Residents can assign different weights to safety, kinship, status, duty, reciprocity, and other goals.
Aggregate outcomes must be derivable from prior physical processes, decisions, and interactions.
Injuries, resources, obligations, institutions, relationships, and ecological changes persist across model calls.
Simulation output does not establish human behavior, consciousness, or personal survival.
Observer / 06
Population, stores, structures, health, territory, institutions, and ecology.
Births, deaths, work, decisions, disputes, projects, migration, and hazards.
Paths from an outcome to prior decisions, observations, constraints, and random draws.
A separate simulation starting from a selected decision or intervention.
Validation / 07
Test continuity measures and controls before connecting cognition to the full settlement.
Run many no-LLM worlds to locate invariant failures, unstable parameters, and trivial outcomes.
Remove memory, relationships, scarcity, institutions, or migration and measure the change in predefined outcomes.
Reconstruct recorded history exactly. Treat changed decisions or new model calls as separate branches.
Publish positive, negative, null, and unstable results with the same protocol and artifact requirements.
Launch acceptance criteria
Known invariant violations in stress ensembles
Replay equivalence for golden histories
Provider failure recovery and compute use
Causal path for every reported outcome
Running unattended before the first public world wakes
Research boundary / 08
December studies operational continuity, not consciousness.
The current experiments measure continuity in commitments, relationships, beliefs, adaptation, and behavior across time and perturbations.
A positive result does not establish subjective experience, personhood, or survival of a human or artificial subject.
Open research / 09
Protocols, parameters, assumptions, and outcome definitions are versioned before confirmatory runs.
The kernel, event model, experiment harnesses, and analysis code are open source.
Recorded runs can be reconstructed and inspected at the event level.
Negative results, model refusals, costs, deviations, and known invalid regions are published.
Claim limit
December is a research system for persistent synthetic agents. It is not a validated model of humanity or a test of consciousness.
Contribute / 10
Inspect the specification, challenge an assumption, contribute code, or propose a test.
Read the complete working book, inspect the implementation, contribute code, or open a research issue.
Suggest a decision, relationship, institution, hazard, or ordinary activity that the model should represent and explain.
December currently uses fictional residents only. Please do not submit anyone’s private life history or nominate a human participant.
Open an issue ↗