# SuperLocalMemory V3.3："活脑"--生物启发式遗忘与认知量化的Zero-LLM智能体记忆系统

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-04-06 08:00
- AIHOT 链接：https://aihot.virxact.com/items/cmo2hssd702teslbazfcv81e2
- 原文链接：https://arxiv.org/abs/2604.04514

## AI 摘要

SuperLocalMemory V3.3（"活脑"）作为本地优先的Zero-LLM智能体记忆系统发布，实现完整认知记忆分类。核心创新包括：Fisher-Rao量化感知距离（FRQAD）以100%精度识别高保真嵌入；艾宾浩斯自适应遗忘曲线实现6.7倍区分力；7通道认知检索（语义、关键词、实体图、时间、扩散激活、巩固、Hopfield联想）在LoCoMo基准零LLM模式下达70.4%，多跳任务提升23.8个百分点。支持长时内隐记忆参数化与自动认知管道，纯CPU运行，月下载超5000次。

## 正文

AI coding agents operate in a paradox: they possess vast parametric knowledge yet cannot remember a conversation from an hour ago. Existing memory systems store text in vector databases with single-channel retrieval, require cloud LLMs for core operations, and implement none of the cognitive processes that make human memory effective. We present SuperLocalMemory V3.3 ("The Living Brain"), a local-first agent memory system implementing the full cognitive memory taxonomy with mathematical lifecycle dynamics. Building on the information-geometric foundations of V3.2 (arXiv:2603.14588), we introduce five contributions: (1) Fisher-Rao Quantization-Aware Distance (FRQAD) -- a new metric on the Gaussian statistical manifold achieving 100% precision at preferring high-fidelity embeddings over quantized ones (vs 85.6% for cosine), with zero prior art; (2) Ebbinghaus Adaptive Forgetting with lifecycle-aware quantization -- the first mathematical forgetting curve in local agent memory coupled to progressive embedding compression, achieving 6.7x discriminative power; (3) 7-channel cognitive retrieval spanning semantic, keyword, entity graph, temporal, spreading activation, consolidation, and Hopfield associative channels, achieving 70.4% on LoCoMo in zero-LLM Mode A; (4) memory parameterization implementing Long-Term Implicit memory via soft prompts; (5) zero-friction auto-cognitive pipeline automating the complete memory lifecycle. On LoCoMo, V3.3 achieves 70.4% in Mode A (zero-LLM), with +23.8pp on multi-hop and +12.7pp on adversarial. V3.2 achieved 74.8% Mode A and 87.7% Mode C; the 4.4pp gap reflects a deliberate architectural trade-off. SLM V3.3 is open source under the Elastic License 2.0, runs entirely on CPU, with over 5,000 monthly downloads.