Skip to content
zensation
🔬

Research overview

Three tracks, architecture and agenda

📐

Methodology

Operational standards and validation

📄

Publications

Preprints, software, identifiers

⚖️

Research ethics

Fundamental-rights nexus and compliance

🏛️

Public sector & funding

Collaborations in the public sector

🧰

Resources

Code, data, citation, open science

AboutOpen SourceDevelopersBlog
Contact
zensation
🔬Research overview📐Methodology📄Publications⚖️Research ethics🏛️Public sector & funding🧰Resources
AboutOpen SourceDevelopersBlogContact

Track A

Memory architectures for autonomous AI systems

„How can AI remember, reason, and learn over time — without losing efficiency, reliability, or methodological traceability along the way?"

A seven-layer memory architecture grounded in neuroscience and tested in a productive application.

Motivation

Why this research

Today's large language models forget. Their context windows are technically bounded, and plain vector stores are not enough to faithfully model the layers of human memory — from a fleeting working memory to consolidated long-term knowledge.

What is missing are architectures that explicitly model consolidation, directed forgetting, confidence propagation, and predictive memory formation. This research answers with an architecture that did not emerge from marketing but from the question how a system at an academic level can maintain its own knowledge base.

Methodological approach

Seven layers, fifteen algorithms, one coordinator

The architecture splits memory into seven functionally differentiated layers — from working memory for active tasks, through episodic memory for concrete experiences, to predictive memory with neuromodulator-driven consolidation. Each layer is addressable through a unified API; a MemoryCoordinator orchestrates storing, retrieving, consolidating, and forgetting.

Fifteen algorithms — each with a peer-reviewed neuroscience source — provide the mechanics: FSRS for directed spaced repetition, Hebbian learning for co-activation, the Ebbinghaus forgetting curve, Bayesian confidence propagation, a two-factor synaptic model, a vmPFC-coupled prediction-error update, and six more. Sleep consolidation simulates offline memory replay.

Core components

The architecture at a glance

7 memory layers

Working, Short-Term, Episodic, Semantic, Procedural, Core, and Predictive Memory — each with its own time scale, persistence, and consolidation logic.

MemoryCoordinator

A unified API across all seven layers: store(), recall(), consolidate(), decay(), reviewQueue(). Routing follows salience and context automatically.

FSRS spaced repetition

Free Spaced Repetition Scheduler — vmPFC-coupled variant with prediction-error update. Facts are reviewed at optimal moments, not on a fixed grid.

Sleep consolidation

Offline memory replay as a methodological core. Selection of important memories for reinforcement; directed pruning of weak associations.

Two-factor synaptic model

Consolidation is driven by two factors — co-activation frequency and a neuromodulator signal. Reproduces experimental findings from the synaptic-tagging literature.

Predictive memory architecture

Six components — NeuromodulatorEngine, ReconsolidationEngine, TripleCopyMemory, PriorityMap, StabilityProtector, MetacognitiveMonitor — model predictive memory formation with bias detection.

Current state

What is publicly available

Open-access preprintarXiv 2604.23878 (opens in new tab)DOI10.5281/zenodo.19353663 (opens in new tab)Source codegithub.com/zensation-ai/zenbrain (opens in new tab)npm packages@zensation/algorithms, @zensation/core (opens in new tab)

Get involved

Collaboration on this research

Enquiries from universities, research consortia or funding programmes — on replication studies, consortium proposals or methodological discussion — are explicitly welcome.

research@zensation.ai

More from this research

Related pages

Three tracks, one core, a shared ethics foundation.

  • Methodology →Pre-registration, reproducibility, external validation, data minimisation — operational standards in detail.
  • Publications →arXiv, Zenodo (DOI), software releases, open-access principles.
  • Resources →Code, replication material, BibTeX citation, licences, identifiers.
  • Research ethics →GDPR Art. 89, AI Act Art. 5, Brokdorf line. Eight mandatory corrections.
  • Public sector & research →Research offerings for BMI, BSI, BBK, universities, research consortia.
  • Principal Investigator →Profile, background, identifiers, contact paths.

Newsletter

No spam. GDPR-compliant.

© 2026 Alexander Bering / ZenSation Enterprise Solutions

HomeResearchMethodologyResearch ethicsPublic sectorPublicationsResourcesZenAIOpen SourceDevelopersTechnologyAboutBlogChangelogPrivacy PolicyLegal Notice
Download on theApp Store
GitHubLinkedInarXivZenodoORCIDScholarSemantic ScholarHuggingFacenpmDiscord