Cost and accuracy of long-term graph memory in distributed LLM-based multi-agent systems

Distributed multi-agent systems use large language models to enable collaborative intelligence while preserving privacy, yet systematic evaluations of long-term memory under network constraints remain limited. This study presents a flexible testbed comparing mem0, a vector-based memory framework, and Graphiti, a graph-based knowledge graph, using the LOCOMO long-context benchmark. Experiments were conducted under unconstrained and constrained network conditions, measuring computational, financial, and accuracy metrics. Results indicate that mem0 significantly outperforms Graphiti in efficiency, with faster loading times, lower resource consumption, and minimal network overhead, while accuracy differences are not statistically significant. Applying a statistical pareto efficiency framework, mem0 is identified as the optimal choice that balances cost and accuracy in DMAS.