Persistent Identity in AI Agents: A Multi-Anchor Architecture for Resilient Memory and Continuity
This addresses the identity problem in AI agents for applications requiring persistent memory, though it is incremental as it builds on existing memory and retrieval methods.
The paper tackles the problem of AI agents losing identity continuity due to catastrophic forgetting from context window overflows, proposing a multi-anchor architecture that achieves efficient retrieval without sacrificing comprehensiveness.
Modern AI agents suffer from a fundamental identity problem: when context windows overflow and conversation histories are summarized, agents experience catastrophic forgetting -- losing not just information, but continuity of self. This technical limitation reflects a deeper architectural flaw: AI agent identity is centralized in a single memory store, creating a single point of failure. Drawing on neurological case studies of human memory disorders, we observe that human identity survives damage because it is distributed across multiple systems: episodic memory, procedural memory, emotional continuity, and embodied knowledge. We present soul.py, an open-source architecture that implements persistent identity through separable components (identity files and memory logs), and propose extensions toward multi-anchor resilience. The framework introduces a hybrid RAG+RLM retrieval system that automatically routes queries to appropriate memory access patterns, achieving efficient retrieval without sacrificing comprehensiveness. We formalize the notion of identity anchors for AI systems and present a roadmap for building agents whose identity can survive partial memory failures. Code is available at github.com/menonpg/soul.py