← 返回
AI智能 中文

Memoria Memory System

Manages AI assistant long-term memory with layered storage for facts, events, skills, context, and fast indexing, including backup and integrity tools.
管理AI助手长期记忆,采用分层存储保存事实、事件、技能和上下文,支持快速索引、备份及完整性工具。
cuilinshen
AI智能 clawhub v1.0.0 1 版本 99875.9 Key: 无需
★ 0
Stars
📥 805
下载
💾 19
安装
1
版本
#ai-assistant#backup#cognitive#knowledge-management#latest#long-term-memory#memory

概述

Memoria System

Overview

Memoria System is a comprehensive long-term memory management system designed for AI assistants. It implements a human-like cognitive memory architecture with distinct layers for different types of information.

Memory Architecture

The system organizes memory into five distinct types, mirroring human cognitive structures:

1. Semantic Memory (semantic/)

Stores factual knowledge, concepts, and general information.

  • facts.md - Personal facts and key information
  • concepts.md - Learned concepts and knowledge
  • knowledge/ - Detailed knowledge entries

2. Episodic Memory (episodic/)

Records events, experiences, and conversations with timestamps.

  • YYYY-MM-DD.md - Daily memory logs
  • events/ - Specific event documentation

3. Procedural Memory (procedural/)

Contains skills, workflows, and learned procedures.

  • skills.md - Acquired skills and capabilities
  • workflows.md - Common procedures and workflows
  • scripts/ - Automation and utility scripts

4. Working Memory (working/)

Holds current session context and active tasks.

  • current.md - Active context and pending items
  • session/ - Session-specific data

5. Index (index/)

Provides fast lookup and search capabilities.

  • tags.json - Tag-based indexing
  • timeline.json - Chronological event index
  • search/ - Search indexes

Tools

memory-backup.sh

Creates incremental backups of the memory system.

Usage:

./memory-backup.sh [options]

Options:

  • --dry-run - Show what would be backed up without doing it
  • --verbose - Show detailed output
  • --path PATH - Override memory path
  • --output PATH - Override backup destination

memory-migrate.sh

Initializes new memory structures or migrates existing ones.

Usage:

./memory-migrate.sh {init|daily [DATE]|migrate [VERSION]}

Commands:

  • init - Initialize memory structure
  • daily [DATE] - Create daily memory file (default: today)
  • migrate [VERSION] - Migrate from specified version

memory-rollback.sh

Restores memory from a previous backup.

Usage:

./memory-rollback.sh {list|rollback BACKUP_NAME [--force]}

Commands:

  • list - List available backups
  • rollback BACKUP_NAME - Restore to specified backup

Options:

  • --force - Skip confirmation prompt

memory-health-check.sh

Validates memory integrity and optionally repairs issues.

Usage:

./memory-health-check.sh [options]

Options:

  • --fix - Automatically fix detected issues
  • --path PATH - Override memory path

Configuration

Edit config.json to customize behavior:

{
  "memory": {
    "base_path": "./memory",
    "structure": { ... }
  },
  "backup": {
    "enabled": true,
    "retention_days": 30,
    "schedule": "0 2 * * *"
  },
  "health_check": {
    "auto_fix": false,
    "check_interval_hours": 24
  }
}

Cron Setup

Add to crontab for automated maintenance:

# Daily backup at 2 AM
0 2 * * * cd /path/to/memoria-system && ./memory-backup.sh

# Weekly health check on Sundays at 3 AM
0 3 * * 0 cd /path/to/memoria-system && ./memory-health-check.sh --fix

Installation

openclaw skill install memoria-system

Requirements

  • Bash 4.0+
  • jq (for JSON processing)
  • tar (for backup compression)

License

MIT

版本历史

共 1 个版本

  • v1.0.0 当前
    2026-03-29 21:06 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

ai-intelligence

Proactive Agent

halthelobster
将AI智能体从任务执行者升级为主动预判需求、持续优化的智能伙伴。集成WAL协议、工作缓冲区、自主定时任务及实战验证模式。Hal Stack核心组件 🦞
★ 836 📥 213,248
ai-intelligence

ontology

oswalpalash
类型化知识图谱,用于结构化智能体记忆与可组合技能。支持创建/查询实体(人员、项目、任务、事件、文档)及关联...
★ 713 📥 243,958
ai-intelligence

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,360 📥 318,618