# Engramme推出"大记忆模型"新架构，宣称解决AI持久记忆难题

- 来源：Chubby♨️ (@kimmonismus)
- 发布时间：2026-04-29 11:41
- AIHOT 分数：40
- AIHOT 链接：https://aihot.virxact.com/items/cmojjbbmj04pjslzp0vef16fe
- 原文链接：https://x.com/kimmonismus/status/2049333106105364935

## AI 摘要

初创公司Engramme构建了一种名为“大记忆模型”的全新AI架构，旨在专门模拟人类记忆的工作方式，而非依赖RAG或向量搜索等现有技术范式。其创始团队拥有超过160篇Nature和ICLR的出版物，并为此关闭了哈佛实验室。该公司认为，持久性记忆是当前AI的关键弱点，其LMM技术旨在为各类应用赋予持久记忆能力，宣称其解决了AI中的核心记忆难题，正如Google与OpenAI分别解决了搜索和语言问题一样。目前产品已开放测试注册。

## 正文

Ok， this is pretty interesting. These guys built a completely new architecture： Large Memory Models. This is designed specifically for how human memory works. Instead of RAG or vector search， this is a different paradigm. Their founders have 160+ publications in Nature and ICLR， and closed their Harvard lab to build this.

### 引用推文

> Engramme：Persistent memory is the Achilles heel of AI. Engramme's Large Memory Models (LMMs) empower every app with persistent memory. Google solved search. OpenAI solve...