Files
nexus/wiki/entities/MemPalace.md
2026-04-28 12:03:10 +08:00

41 lines
1.3 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
title: "MemPalace"
type: entity
tags: [AI-Memory, Memory-Backend, Local-First, Vector-DB, ChromaDB]
sources: [ai-memory-tools-two-camps]
last_updated: 2026-04-15
---
## Basic Info
- **Type**: 产品 / AI Memory Tool
- **GitHub**: 46.2k stars
- **Category**: Camp 1 — Memory Backend
- **Website**: mempalace.app
## Summary
本地优先的逐字记忆工具。不同于提取事实MemPalace 逐字存储对话并组织为 Wings实体、Rooms主题、Drawers原始内容结构通过 ChromaDB 搜索。
## Core Features
- 本地优先架构(数据完全存储在本地)
- 逐字存储对话verbatim memory
- Wings/Rooms/Drawers 组织结构:
- **Wings**实体entities
- **Rooms**主题topics
- **Drawers**:原始内容
- ChromaDB 向量搜索
## Benchmark Results
LongMemEval 基准测试结果:
- 纯语义搜索(无 LLM**96.6%** 检索召回率
- 混合管道:**98.4%**
- LLM 重排:**99%+**
## Key Limitation
- 逐字存储线性增长——对话越多,占用越大
- 无压缩、无综合
- 擅长"找到三周前我说的话",不适合"给我跨五个项目的当前工作状态"
## Connections
- [[ai-memory-tools-two-camps]] ← 来源 ← MemPalace 拥有 Camp 1 中最高 LongMemEval 基准
- [[Memory-Backend]] ← 属于 ← MemPalace 是 Memory Backend 范式的代表工具