Memory for AI Agents: A Survey of Architectures, Systems, and the Cloud Native Paradigm
Aim: This study examines persistent memory architectures for large language models (LLMs) and AI agents, develops a functional taxonomy of memory systems, evaluates emerging approaches to context-management limitations, and assesses how cloud-native services can support agent memory implementation. Methods: The study synthesizes literature on persistent agent memory, attention-efficient architectures, in-context learning, and inference-time adaptation. The study uses a thematic framework to compare the mechanisms, computational implications, and implementation requirements of different memory approaches. The study also presents a case study of Google Cloud’s memory ecosystem, examining Memorystore, AlloyDB with pgvector, Vertex AI Vector Search, and the conceptual Agent Engine. Results: The synthesis indicates that efficient attention mechanisms, inference-time adaptation, and persistent external memory address different aspects of the agent-memory problem and should not be treated as interchangeable solutions. The Google Cloud case study illustrates how cloud-native services can provide complementary capabilities for implementing persistent agent memory. Conclusion: The study concludes that effective agent memory requires a coordinated approach to memory representation, retrieval, updating, consolidation, and evaluation. Increasing context-window capacity alone does not adequately address the architectural limitations associated with persistent memory in LLM-based agents. Recommendation: The study recommends developing reproducible benchmarks and cost-aware evaluation frameworks to compare memory architectures under realistic agent workloads.
Authors
- Nitheesh Varma Varadaraju
Publication Details
- Journal
- American Journal of Technology
- Published
- 2026-11-16
- DOI
- https://doi.org/10.58425/ajt.v5i13.645
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.00