We present MemX, a local-first long-term memory system for AI assistants with stability-oriented retrieval design. MemX is implemented in Rust on top of libSQL and an OpenAI-compatible embedding API, providing persistent, searchable, and explainable memory for conversational agents. Its retrieval pipeline applies vector recall, keyword recall, Reciprocal Rank Fusion (RRF), four-factor re-ranking, and a low-confidence rejection rule that suppresses spurious recalls when no answer exists in the memory store. We evaluate MemX on two axes. First, two custom Chinese-language benchmark suites (43 queries, <=1,014 records) validate pipeline design: Hit@1=91.3% on a default scenario and 100% under high confusion, with conservative miss-query suppression. Second, the LongMemEval benchmark (500 queries, up to 220,349 records) quantifies system boundaries across four ability types and three storage granularities. At fact-level granularity the system reaches Hit@5=51.6% and MRR=0.380, doubling session-level performance, while temporal and multi-session reasoning remain challenging (<=43.6% Hit@5). FTS5 full-text indexing reduces keyword search latency by 1,100x at 100k-record scale, keeping end-to-end search under 90 ms. Unlike Mem0 and related work that targets end-to-end agent benchmarks, MemX focuses on a narrower, reproducible baseline: local-first deployment, structural simplicity, explainable retrieval, and stability-oriented design.

翻译：本文提出MemX，一种面向AI助手的本地优先长期记忆系统，采用稳定性导向的检索设计。MemX基于libSQL与OpenAI兼容的嵌入API以Rust语言实现，为对话智能体提供持久化、可检索且可解释的记忆功能。其检索流程依次执行向量召回、关键词召回、 Reciprocal Rank Fusion（RRF）融合、四因子重排序，并采用低置信度拒止规则以在记忆库中无答案时抑制虚假召回。我们从两个维度评估MemX：首先，在两个定制化中文基准测试集（43条查询，≤1,014条记录）上验证流程设计——默认场景下Hit@1=91.3%，高混淆场景下达到100%，且对误查询具有保守抑制能力；其次，通过LongMemEval基准（500条查询，最高220,349条记录）量化系统在四种能力类型与三种存储粒度下的性能边界。在事实粒度层面，系统达到Hit@5=51.6%与MRR=0.380，较会话级性能提升一倍，而时序推理与多会话推理仍具挑战（Hit@5≤43.6%）。FTS5全文索引在十万条记录规模下将关键词搜索延迟降低1,100倍，端到端检索全程保持90毫秒以内。与面向端到端智能体基准的Mem0及相关研究不同，MemX聚焦于更专注、可复现的基础特性：本地优先部署、结构简洁性、可解释检索及稳定性导向设计。