ElephantBroker: A Knowledge-Grounded Cognitive Runtime for Trustworthy AI Agents
Cristian Lupascu, Alexandru Lupascu

TL;DR
ElephantBroker introduces a comprehensive, verifiable cognitive runtime for AI agents that integrates knowledge graphs and vector stores to enhance factual grounding, safety, and trustworthiness in high-stakes multi-turn interactions.
Contribution
It presents a modular, open-source cognitive system unifying knowledge graphs and vector stores with advanced safety, verification, and management features for trustworthy AI agent deployment.
Findings
Validated through over 2,200 tests confirming subsystem correctness.
Supports diverse deployment tiers and safety configurations.
Enables durable, verifiable, and safe agent memory management.
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsExplainable Artificial Intelligence (XAI) · Scientific Computing and Data Management · Access Control and Trust
