RhizoDB: A Bounded Activation-Flow Architecture for Graph-Based Memory Systems
Abstract
RhizoDB is a graph-based memory architecture for agentic systems, grounded in bounded activation flow, stability-modulated temporal decay, depth-limited propagation, periodic washout, and structural pruning. This technical report formulates RhizoDB as a non-linear dynamical system over a mutable directed graph and relates its local activation-control mechanisms to broader stabilization approaches for repeated signal composition.
Fields of Study & Subjects
Advanced Graph Neural Networks
Complex Network Analysis Techniques
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 15 June 2026
- Language
- EN