Jev-Mem：受 System One/Two 启发的 agent 记忆架构
报告提出 Jev-Mem，用轻量控制器管记忆存取与检索，构建快 6.6 倍、查询延迟降 36.7%，LoCoMo 得分 0.777。
Banger report on building faster memory for AI Agents. If your agent's memory layer is slow, this design is worth a look. Great weekend read. It proposes a new agentic memory architecture, Jev-Mem, inspired by System-One/System-Two cognition. This builds agent memory 6.6x faster and cuts query latency by 36.7% while scoring higher on LoCoMo. In this system, a lightweight controller makes the memory decisions. It assigns memory types and relations when storing, and handles routing, retrieval budget, graph traversal, scoring and stopping when reading. The LLM is called only for final reasoning and answer writing. On LoCoMo, it scores 0.777 overall with an LLM judge, an 11.0% relative improvement over the strongest baseline. Memory construction takes 158 seconds, and average query latency drops to 0.93 seconds. Paper: https://academy.dair.ai/papers/jev-mem-system-one-controlled-agentic-memory-for-efficient-ai-agents-2609.23986