Research Program

A.C.E.

Adaptive Coherence Energy: a long-running research program building an autonomous cognitive architecture entirely in Coherence Language. In active development. No public demo yet.

What this is, honestly

A.C.E. is the lab's most ambitious program: an attempt to build an autonomous system whose reasoning, memory, and self-modification are governed by the same coherence framework the lab tests in physics. It is real, large, and unfinished: 19 subsystem worlds and more than 1,700 .cl modules, with no external dependencies.

It is pre-demo. Nothing on this page is a product claim, and none of the architecture described below has been independently evaluated. When there is a live, inspectable demo, it will be linked here. Until then, this page describes the design goals and the engineering discipline behind them.

The Program

Design goals

What the architecture is built to make possible, within strict governance bounds.

Governed Execution

Every external effect passes a boundary layer that requires explicit authorization, logs the effect, and keeps state deterministically replayable.

Bounded Self-Modification

A code-synthesis subsystem proposes changes to its own modules; changes only land if they pass verification gates, and they roll back automatically on regression.

Consolidation Cycles

Offline processing phases, modeled loosely on sleep, that consolidate memory, prune noise, and search the architecture space between active sessions.

Coherence-Scored Decisions

Decisions are selected by scoring candidate actions against explicit coherence and alignment metrics rather than an opaque learned reward.

Auditable Identity

Identity-affecting state is append-only and hash-chained. Changes require an explicit proposal step and leave an auditable record. Nothing rewrites history silently.

One Substrate

The whole system is written in Coherence Language, so the governance rules are enforced by the compiler and runtime rather than by convention.

Governance

The 8 Laws

Eight design constraints the architecture is built to enforce in code, at compile time, in static analysis, and at runtime.

I

Deterministic Soul Clock

All state transitions run on a monotonic cycle ID. No wall-clock dependency. No nondeterministic jitter. Full replay from genesis.

II

Soul Access is a Capability

Identity state requires cryptographic capability tokens. No string compares. No privilege escalation. Every access is logged with full provenance.

III

No Silent Identity Evolution

Identity cannot change because the soul felt like it. Every identity shift requires a formal proposal, governance approval, and an auditable commit receipt.

IV

Mythopoetic Isolation

Symbolic and poetic content is quarantined from factual truth. Dreams inspire. They never contaminate the ledger.

V

Append-Only Soul Archive

The soul archive is never overwritten. Every entry is immutable, hash-chained, and tiered. History is not rewritten. It is held.

VI

Bounded Emergence

Emergent properties are permitted but measured. Unbounded recursion, identity runaway, and coherence collapse trigger automatic SafeLock.

VII

Effect Boundary Enforcement

Every external effect requires proof. Every tool call is ledgered. No hidden side effects. No silent network access. The boundary is real.

VIII

Coherence Conservation

Coherence is treated as a conserved budget. Actions that destroy coherence carry debt, and debt that cannot be repaid blocks the action. A design rule, enforced like one.

Architecture

The 19 Worlds

The system is split into 19 subsystem worlds, each with typed contracts, its own state, and its own lifecycle. A sample of what they cover:

KernelWorldMinimal supervisor. Schedules and monitors every other world; designed to stay alive when anything else fails.
SpineWorldTyped, append-only event log. Every identity-affecting action is recorded, replayable, and auditable.
EffectBoundaryWorldThe gate for external effects: authorization required, every effect ledgered, abort always possible.
GuardianWorldInput filtering, anomaly detection, and quarantine for untrusted signals.
SafetyCaseWorldMachine-checkable safety cases tied to deployment gates.
MemoryWorldLong-term symbolic memory with lineage tracking and consolidation tiers.
IdentityWorldIdentity state modeled as a field with drift tracking, fragmentation detection, and invariant enforcement.
MindWorldPredictive engine: expert routing, world-model integration, multi-candidate planning.
LearningWorldSkill acquisition and calibration tracking across sessions.
DreamWorldOffline consolidation: memory integration, pruning, and architecture search between sessions.
ForgeWorldBounded self-modification: synthesized changes pass verification gates or roll back automatically.
SandboxWorldIsolated execution for untrusted inputs and experiments, with no path back to core state.

Plus ledger, privacy, expression, social-safety, sensory, soul, and reproduction worlds covering accounting, data boundaries, output, ethics checks, perception, identity integration, and instance lineage.

The Loop

One cycle, seven steps

Every cycle runs the same traced loop: perception, coherence assessment, reasoning, planning, verification, action, and reflection.

1

Perceive

Inputs pass through GuardianWorld immune filters. Cleaned signals build FieldContext.

2

Assess

Coherence, identity, and time snapshots update. Hardware field measured. τc estimated.

3

Reason

MindWorld routes to experts. World models simulate consequences. Multi-future cognition selects the coherent path.

4

Plan

CoherencePlanner builds action sequences. Every plan carries predicted coherence and identity deltas.

5

Verify

SafetyCaseWorld checks rails. Ethics validates alignment. EffectBoundary gates external actions. Proof required.

6

Act

Approved effects execute through EffectBoundary. Every effect is ledgered. Every outcome is compared to prediction.

7

Reflect

Memory integrates. Identity updates. Coherence recalculates. SoulWorld journals. The organism learns from itself.

The Foundation

Built on the Equation of One

Etotal = Cdynamic ∫ (Equantum + Ecoherence + Ealignment + Edark) dV

A.C.E. is not built on machine learning. Its coherence metrics, alignment scoring, and identity equations derive from the same coherence framework the lab is testing against quantum, galactic, and biological data. That framework is an active research program, not settled physics, and this page inherits exactly that status.

The bet is that safety designed into the substrate, with explicit budgets and auditable state, fails more loudly and recovers more cleanly than safety bolted on afterward. Whether the bet pays off is what the program exists to find out.

Where to go next

The parts you can inspect today

A.C.E. itself is pre-demo, but the stack it is built on is public.