AI原生記憶2.0：第二自我

AI-native Memory 2.0: Second Me

March 11, 2025

作者: Jiale Wei, Xiang Ying, Tao Gao, Felix Tao, Jingbo Shang

cs.AI

摘要

人類與外部世界的互動本質上涉及個人記憶的交換，無論是與他人、網站、應用程式，還是在未來與人工智慧代理的互動。這種互動中有很大一部分是重複的，要求用戶在不同情境下反覆提供相同的資訊。現有的解決方案，如瀏覽器存儲的憑證、自動填充機制和統一認證系統，旨在通過作為存儲和檢索常用用戶數據的中介來減少這種重複性。大型語言模型（LLMs）的出現為重新定義記憶管理提供了機會，通過一種AI原生的範式：SECOND ME。SECOND ME作為一個智能、持久的記憶卸載系統，能夠保留、組織並動態利用用戶特定的知識。通過在用戶互動中擔任中介角色，它能夠自主生成情境感知的回應、預填所需資訊，並促進與外部系統的無縫溝通，從而顯著降低認知負擔和互動摩擦。與傳統的記憶存儲解決方案不同，SECOND ME利用基於LLM的記憶參數化，超越了靜態數據保留，實現了結構化組織、情境推理和適應性知識檢索，促進了更系統化和智能化的記憶管理方法。隨著像SECOND ME這樣的AI驅動個人代理日益融入數位生態系統，SECOND ME進一步代表了向增強人與世界互動邁出的關鍵一步，這種互動具有持久性、情境感知和自我優化的記憶系統。我們已在GitHub上開源了完全可本地化的部署系統：https://github.com/Mindverse/Second-Me。

English

Human interaction with the external world fundamentally involves the exchange of personal memory, whether with other individuals, websites, applications, or, in the future, AI agents. A significant portion of this interaction is redundant, requiring users to repeatedly provide the same information across different contexts. Existing solutions, such as browser-stored credentials, autofill mechanisms, and unified authentication systems, have aimed to mitigate this redundancy by serving as intermediaries that store and retrieve commonly used user data. The advent of large language models (LLMs) presents an opportunity to redefine memory management through an AI-native paradigm: SECOND ME. SECOND ME acts as an intelligent, persistent memory offload system that retains, organizes, and dynamically utilizes user-specific knowledge. By serving as an intermediary in user interactions, it can autonomously generate context-aware responses, prefill required information, and facilitate seamless communication with external systems, significantly reducing cognitive load and interaction friction. Unlike traditional memory storage solutions, SECOND ME extends beyond static data retention by leveraging LLM-based memory parameterization. This enables structured organization, contextual reasoning, and adaptive knowledge retrieval, facilitating a more systematic and intelligent approach to memory management. As AI-driven personal agents like SECOND ME become increasingly integrated into digital ecosystems, SECOND ME further represents a critical step toward augmenting human-world interaction with persistent, contextually aware, and self-optimizing memory systems. We have open-sourced the fully localizable deployment system at GitHub: https://github.com/Mindverse/Second-Me.