ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems

Overview

ZenBrain is a 7-layer neuroscience-inspired memory architecture for autonomous AI systems. It bridges the gap between biological memory principles and practical AI system design, delivering measurable performance improvements across long-context recall, memory stability, and knowledge retrieval tasks.

Paper: ZenBrain v5 (Zenodo) | DOI: 10.5281/zenodo.19353663

Key Results (7 Experiments)

Experiment	Metric	Result
Exp 1 — LoCoMo Retrieval	F1 score	+21.6% vs. Flat Store
Exp 2 — Layer Ablation	Storage efficiency	+47.4% vs. single-layer
Exp 3 — Retention Curves	Retention@30d	89.9% (vs. 0% pure Ebbinghaus)
Exp 4 — Sleep Consolidation	Memory stability	+37.0% vs. no-sleep baseline
Exp 5 — Hebbian Retrieval	Precision@5	0.955
Exp 6 — Bayesian Confidence	Confidence AUC	0.797 (+49.5% vs. 0.533)
Exp 7 — MemoryArena	Retrieval accuracy	+19.5% vs. Flat Store

Experiments 1, 2, 4, 5, 7 use synthetic benchmark data (FakeEmbeddingProvider). Real-data runs require the LoCoMo and MemoryArena datasets — see experiments/README.md.

Architecture: 7 Memory Layers

Layer 1: Working Memory       — Active task focus (capacity-limited, 7±2 items)
Layer 2: Episodic Memory      — Concrete experiences with temporal context
Layer 3: Semantic Memory      — Abstracted facts and relationships
Layer 4: Procedural Memory    — Skills and how-to knowledge
Layer 5: Short-Term Memory    — Session context buffer
Layer 6: Long-Term Memory     — Persistent cross-session knowledge
Layer 7: Core Memory          — Pinned identity and values (Letta-pattern)

Key algorithms:

Hebbian Learning (co-activation strengthening, decay, normalization)
FSRS Spaced Repetition (optimal review scheduling)
Bayesian Confidence Propagation (uncertainty quantification)
Sleep Consolidation (Stickgold & Walker 2013 — memory replay simulation)
Ebbinghaus Decay (forgetting curve modeling)
Contextual Retrieval (Anthropic method, +67% retrieval accuracy)

Installation

# Core algorithms (zero dependencies)
npm install @zensation/algorithms

# Memory layer orchestration
npm install @zensation/core

# PostgreSQL + pgvector adapter
npm install @zensation/adapter-postgres

# SQLite adapter (zero-config)
npm install @zensation/adapter-sqlite

Quick Start

import { MemoryCoordinator } from '@zensation/core';
import { PostgresAdapter } from '@zensation/adapter-postgres';

const memory = new MemoryCoordinator({
  adapter: new PostgresAdapter({ connectionString: process.env.DATABASE_URL }),
});

// Store a memory across all relevant layers
await memory.store({
  content: 'ZenBrain uses Hebbian learning for knowledge graph strengthening',
  type: 'semantic',
  importance: 0.9,
});

// Recall with confidence scores
const results = await memory.recall('Hebbian learning', { topK: 5 });
// Returns facts with 95% confidence intervals

Citation

@misc{bering2026zenbrain,
  title   = {ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems},
  author  = {Bering, Alexander},
  year    = {2026},
  doi     = {10.5281/zenodo.19353663},
  url     = {https://zenodo.org/records/19413933},
  note    = {Zenodo Preprint}
}

License

Apache 2.0 — see LICENSE

Downloads last month: -; Downloads are not tracked for this model. How to track

alexanderbering
/

zenbrain