BeastXA Memory Pro
Stop losing context. Start remembering everything.
What It Does
- 1. Structured Session Notes — auto-maintained
session-notes.md captures your current work state - Smart Memory Split — breaks large MEMORY.md into topic files with an index
- Auto Maintenance — daily cleanup + weekly deep organization via cron
- Anti-Amnesia — enhanced compaction saves critical context before compression
Quick Start
CODEBLOCK0
That's it. Everything else is automatic.
What Gets Created
CODEBLOCK1
How It Works
Three-Layer Memory
| Layer | File | Purpose | Update Frequency |
|---|
| Session | INLINECODE1 | Current work state | Every compaction |
| Daily |
YYYY-MM-DD.md | Raw daily log | Every significant event |
| Topics |
topics/*.md | Long-term organized memory | Daily cron |
Anti-Amnesia System
Before each context compaction:
- 1. Saves current task, recent decisions, errors, and next steps
- Writes to both
session-notes.md and daily log - After compaction, agent reads session-notes and resumes seamlessly
Auto Maintenance Crons
- - Daily (23:30) — extracts key decisions and lessons from today's log into topic files
- Weekly (Sunday 23:00) — deduplicates, merges, trims topic files; verifies index
Manual Commands
Split an existing MEMORY.md:
python3 scripts/split_memory.py --input MEMORY.md --output memory/topics/
- - Reads your MEMORY.md, detects topic boundaries (## headers)
- Creates one file per topic in INLINECODE5
- Generates
memory/MEMORY-INDEX.md with pointers - Original file untouched — zero risk
Verify installation:
CODEBLOCK3
Configuration
The install script adds compaction enhancement to your OpenClaw config:
CODEBLOCK4
You can customize the compaction instructions to match your workflow.
FAQ
Will it overwrite my existing MEMORY.md?
Never. The split script only reads it. Your original stays intact.
Does it send data anywhere?
No. Everything is local Markdown files. No APIs, no cloud, no external services.
Can I use it with other memory skills?
Yes. It only creates files and cron jobs — no core modifications.
What if I don't like the topic categories?
Edit them freely. They're just Markdown files. The cron will respect your structure.
Requirements
- - OpenClaw 2026.3.x or later
- Python 3.8+ (for split script)
- That's it
BeastXA Memory Pro
别再丢失上下文。开始记住一切。
功能说明
- 1. 结构化会话笔记 — 自动维护的 session-notes.md 记录当前工作状态
- 智能记忆拆分 — 将大型 MEMORY.md 拆分为带索引的主题文件
- 自动维护 — 通过 cron 实现每日清理 + 每周深度整理
- 防遗忘机制 — 增强型压缩在压缩前保存关键上下文
快速开始
bash
安装
clawhub install beastxa-memory-pro
运行设置(交互式,约需30秒)
bash scripts/install.sh
就这样。其余一切自动完成。
生成的文件结构
your-workspace/
├── memory/
│ ├── session-notes.md # 实时会话状态(自动更新)
│ ├── MEMORY-INDEX.md # 主题文件目录
│ ├── YYYY-MM-DD.md # 每日日志(自动追加)
│ └── topics/ # 按主题组织
│ ├── projects.md
│ ├── decisions.md
│ ├── lessons.md
│ └── ... # 根据内容自动生成
工作原理
三层记忆架构
| 层级 | 文件 | 用途 | 更新频率 |
|---|
| 会话 | session-notes.md | 当前工作状态 | 每次压缩 |
| 每日 |
YYYY-MM-DD.md | 原始每日日志 | 每次重要事件 |
| 主题 | topics/*.md | 长期组织记忆 | 每日定时任务 |
防遗忘系统
每次上下文压缩前:
- 1. 保存当前任务、近期决策、错误和下一步计划
- 同时写入 session-notes.md 和每日日志
- 压缩后,代理读取会话笔记并无缝恢复
自动维护定时任务
- - 每日(23:30) — 从当日日志中提取关键决策和经验教训到主题文件
- 每周(周日23:00) — 去重、合并、精简主题文件;验证索引
手动命令
拆分现有的 MEMORY.md:
bash
python3 scripts/split_memory.py --input MEMORY.md --output memory/topics/
- - 读取您的 MEMORY.md,检测主题边界(## 标题)
- 在 memory/topics/ 中为每个主题创建一个文件
- 生成带索引的 memory/MEMORY-INDEX.md
- 原文件保持不变 — 零风险
验证安装:
bash
bash scripts/verify.sh
配置
安装脚本会向您的 OpenClaw 配置添加压缩增强功能:
json
{
agents: {
defaults: {
compaction: {
memoryFlush: {
enabled: true,
prompt: 压缩前内存刷新。将持久化记忆存储到 memory/YYYY-MM-DD.md...
},
instructions: 保留:用户决策、文件路径、错误与修复、当前任务、下一步计划...
}
}
}
}
您可以根据工作流程自定义压缩指令。
常见问题
会覆盖我现有的 MEMORY.md 吗?
绝不会。拆分脚本仅读取它。您的原始文件保持完整。
会向任何地方发送数据吗?
不会。所有内容都是本地 Markdown 文件。无 API、无云端、无外部服务。
可以与其他记忆技能一起使用吗?
可以。它仅创建文件和定时任务 — 无核心修改。
如果我不喜欢主题分类怎么办?
可自由编辑。它们只是 Markdown 文件。定时任务会尊重您的结构。
系统要求
- - OpenClaw 2026.3.x 或更高版本
- Python 3.8+(用于拆分脚本)
- 仅此而已