Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ElephantBroker: A Knowledge-Grounded Cognitive Runtime for Trustworthy AI Agents

Cristian Lupascu, Alexandru Lupascu

Abstract

Large Language Model based agents increasingly operate in high stakes, multi turn settings where factual grounding is critical, yet their memory systems typically rely on flat key value stores or plain vector retrieval with no mechanism to track the provenance or trustworthiness of stored knowledge. We present ElephantBroker, an open source cognitive runtime that unifies a Neo4j knowledge graph with a Qdrant vector store through the Cognee SDK to provide durable, verifiable agent memory. The system implements a complete cognitive loop (store, retrieve, score, compose, protect, learn) comprising a hybrid five source retrieval pipeline, an eleven dimension competitive scoring engine for budget constrained context assembly, a four state evidence verification model, a five stage context lifecycle with goal aware assembly and continuous compaction, a six layer cheap first guard pipeline for safety enforcement, an AI firewall providing enforceable tool call interception and multi tier safety scanning, a nine stage consolidation engine that strengthens useful patterns while decaying noise, and a numeric authority model governing multi organization identity with hierarchical access control. Architectural validation through a comprehensive test suite of over 2,200 tests spanning unit, integration, and end to end levels confirms subsystem correctness. The modular design supports three deployment tiers, five profile presets with inheritance, multi gateway isolation, and a management dashboard for human oversight, enabling configurations from lightweight memory only agents to full cognitive runtimes with enterprise grade safety and auditability.

ElephantBroker: A Knowledge-Grounded Cognitive Runtime for Trustworthy AI Agents

Abstract

Large Language Model based agents increasingly operate in high stakes, multi turn settings where factual grounding is critical, yet their memory systems typically rely on flat key value stores or plain vector retrieval with no mechanism to track the provenance or trustworthiness of stored knowledge. We present ElephantBroker, an open source cognitive runtime that unifies a Neo4j knowledge graph with a Qdrant vector store through the Cognee SDK to provide durable, verifiable agent memory. The system implements a complete cognitive loop (store, retrieve, score, compose, protect, learn) comprising a hybrid five source retrieval pipeline, an eleven dimension competitive scoring engine for budget constrained context assembly, a four state evidence verification model, a five stage context lifecycle with goal aware assembly and continuous compaction, a six layer cheap first guard pipeline for safety enforcement, an AI firewall providing enforceable tool call interception and multi tier safety scanning, a nine stage consolidation engine that strengthens useful patterns while decaying noise, and a numeric authority model governing multi organization identity with hierarchical access control. Architectural validation through a comprehensive test suite of over 2,200 tests spanning unit, integration, and end to end levels confirms subsystem correctness. The modular design supports three deployment tiers, five profile presets with inheritance, multi gateway isolation, and a management dashboard for human oversight, enabling configurations from lightweight memory only agents to full cognitive runtimes with enterprise grade safety and auditability.

Paper Structure

This paper contains 61 sections, 3 equations, 2 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Motivation
  3. Current Approaches and Their Limitations
  4. Research Contribution
  5. Background and Related Work
  6. Knowledge Graphs for Language Model Grounding
  7. Retrieval-Augmented Generation
  8. Agent Memory and Cognitive Architectures
  9. Contemporary Agent Memory Systems
  10. Trustworthy AI and Verification
  11. LLM Safety and Guardrails
  12. Proposed Cognitive Runtime
  13. Architecture Overview
  14. Data Model and Actor Hierarchy
  15. Scope System
  16. ...and 46 more sections

Figures (2)

  • Figure 1: Four-layer architecture of ElephantBroker. Thin TypeScript adapters in Layer A forward requests via HTTP to the Python runtime in Layer B, which delegates storage and search to the Cognee knowledge plane in Layer C, backed by the infrastructure services in Layer D.
  • Figure 2: Claim verification state machine with associated confidence multipliers $m_v$. Each transition is driven by the type of evidence attached. Dashed arrows indicate explicit rejection, which is possible from any non-terminal state.