Large Language Models (LLMs) are increasingly deployed as long-term interactive agents, yet their limited context windows make it difficult to sustain coherent behavior over extended interactions. Existing memory systems often store isolated records and retrieve fragments, limiting their ability to consolidate evolving user states and resolve conflicts. We introduce EverMemOS, a self-organizing memory operating system that implements an engram-inspired lifecycle for computational memory. Episodic Trace Formation converts dialogue streams into MemCells that capture episodic traces, atomic facts, and time-bounded Foresight signals. Semantic Consolidation organizes MemCells into thematic MemScenes, distilling stable semantic structures and updating user profiles. Reconstructive Recollection performs MemScene-guided agentic retrieval to compose the necessary and sufficient context for downstream reasoning. Experiments on LoCoMo and LongMemEval show that EverMemOS achieves state-of-the-art performance on memory-augmented reasoning tasks. We further report a profile study on PersonaMem v2 and qualitative case studies illustrating chat-oriented capabilities such as user profiling and Foresight. Code is available at https://github.com/EverMind-AI/EverMemOS.

翻译：大型语言模型（LLM）正越来越多地被部署为长期交互式智能体，但其有限的上下文窗口使其难以在长期交互中维持连贯的行为。现有的记忆系统通常存储孤立的记录并检索片段，限制了其整合不断演变的用户状态和解决冲突的能力。我们提出了EverMemOS，一种自组织记忆操作系统，它实现了受记忆印迹启发的计算记忆生命周期。情景痕迹形成模块将对话流转换为MemCell，以捕获情景痕迹、原子事实和有时限的前瞻信号。语义巩固模块将MemCell组织为主题化的MemScene，提炼稳定的语义结构并更新用户画像。重构式回忆模块执行MemScene引导的自主检索，为下游推理组合必要且充分的上下文。在LoCoMo和LongMemEval上的实验表明，EverMemOS在记忆增强推理任务上达到了最先进的性能。我们进一步报告了在PersonaMem v2上的画像研究，以及展示面向聊天能力的定性案例研究，例如用户画像和前瞻功能。代码可在https://github.com/EverMind-AI/EverMemOS获取。