Agent Brain: A Biologically Inspired Memory System for Autonomous AI Agents, with Head-to-Head Evaluation on LongMemEval

This technical report describes Agent Brain, a biologically inspired memory system for autonomous AI agents. In contrast to stateless Large Language Model interactions, Agent Brain provides persistent, weighted, and self-organizing memory that emulates human cognitive processes: perception, storage, retrieval, consolidation, and forgetting. The system integrates eleven successive layers including a Perception Gate, Deduplication Guard, typed memory storage (episodic/semantic/procedural), Named Entity Recognition (flair/ner-german-large, F1 92.31%), a Knowledge Graph, LLM-based Query Expansion, Hybrid Search via Reciprocal Rank Fusion, Cross-Encoder Re-Ranking, an implicit Feedback Loop based on the Free Spaced Repetition Scheduler (FSRS), a nightly five-phase Dream Cycle, and complete Workspace Isolation with Row-Level Security. Head-to-head evaluation on LongMemEval. On the public weaviate/longmemeval-m-cleaned benchmark (500 QA pairs across 510 multi-turn workspaces, GPT-4o judge), Agent Brain achieves 71.7% accuracy, outperforming the next-best publicly reported memory system (Zep, 63.8%) by 7.9 percentage points, Mem0 (49.0%) by 22.7 pp, LangMem (47.1%) by 24.6 pp, and OpenAI Memory (40.2%) by 31.5 pp. We also report transparently a 1.9 pp regression when enabling the Dream Cycle consolidation pipeline, and a 2.2 pp gap versus our own pgvector-only control, discussed in §15.4. The system has been in production use since early 2026 for Swiss property management (Immobilienbewirtschaftung) with over 5,000 memories, 10,000 entities, and eight specialized agents. Reproducibility: All evaluation scripts, ingestion code, and judge configurations released under MIT license at github.com/AgentBrainHQ/agentbrain-benchmarks. Version 2 adds the LongMemEval head-to-head benchmark section (§15) to the April 2026 preprint.