什么是 Brain CMS？

Brain CMS 是一款先进的连续记忆系统（CMS），旨在彻底改变 AI 智能体管理长期信息的方式。该系统不依赖于消耗过度 Token 的单一、臃肿的记忆文件，而是实现了一种受大脑启发的层级结构。它利用语义模式、海马体式路由以及持久的 LanceDB 向量存储，提供稀疏、频率门控的记忆加载。作为更具技术性的 Openclaw Skills 之一，它使智能体能够在长期运行的项目中保持深层上下文，同时显著降低运营成本。

下载入口:https://github.com/openclaw/skills/tree/main/skills/harrey401/brain-cms

安装与下载

1. ClawHub CLI

从源直接安装技能的最快方式。

2. 手动安装

将技能文件夹复制到以下位置之一

优先级：工作区 > 本地 > 内置

3. 提示词安装

将此提示词复制到 OpenClaw 即可自动安装。

Brain CMS 应用场景

• 为处理复杂的跨月项目的智能体建立持久的长期记忆。
• 通过用稀疏模式加载取代扁平上下文注入，降低 Token 消耗和 API 成本。
• 将海量的特定领域知识组织成可检索的语义层。
• 通过模拟用于数据整合的 NREM 和 REM 睡眠周期，自动进行记忆维护。

1. 智能体以精简的核心上下文和最近的每日日志启动，以最小化初始 Token 使用。
2. 当提到特定话题时，系统会咨询 INDEX.md 路由以触发并加载相关的语义模式。
3. 对于模糊或复杂的查询，系统使用本地嵌入对 LanceDB 向量存储执行语义相似度搜索。
4. 在 NREM 睡眠周期（停机时运行）期间，系统压缩情境日志并将高显著性事件提升到 ANCHORS.md 存储中。
5. 在每周一次的 REM 睡眠周期中，通过 Ollama 运行的本地大模型（LLM）将新信息合成并整合到长期记忆架构中。

Brain CMS 配置指南

在继续使用这些 Openclaw Skills 组件之前，请确保已安装 Python 3.10+ 和 Ollama：

# 1. 运行专用安装程序
python3 ~/.openclaw/workspace/skills/brain-cms/install.py

# 2. 将初始模式索引到向量存储中
cd ~/.openclaw/workspace/memory_brain
.venv/bin/python3 index_memory.py

# 3. 验证检索功能
.venv/bin/python3 query_memory.py "test topic" --sources-only

Brain CMS 数据架构与分类体系

Brain CMS 将数据组织在五个不同的层级中，以优化检索和上下文：

name: brain-cms
description: Continuum Memory System (CMS) for OpenClaw agents. Replaces flat MEMORY.md with a brain-inspired multi-layer memory architecture — semantic schemas, a hippocampal router (INDEX.md), vector store (LanceDB + nomic-embed-text), and automated NREM/REM sleep cycles for consolidation. Based on neuroscience research (LTP, spreading activation, CMS theory). Use when setting up persistent agent memory, improving context efficiency, or reducing token cost on long-running agents. Triggers: brain, memory system, CMS, long-term memory, vector store, sleep cycle, NREM, REM, memory architecture, semantic memory, context efficiency.
metadata:
  openclaw:
    emoji: ??
    requires:
      bins: ["python3", "ollama"]
    install:
      - id: python-deps
        kind: shell
        label: "Install Python dependencies"
        command: "cd ~/.openclaw/workspace/memory_brain && python3 -m venv .venv && .venv/bin/pip install lancedb numpy pyarrow requests --quiet"
      - id: ollama-models
        kind: shell
        label: "Pull Ollama models (nomic-embed-text + llama3.2:3b)"
        command: "ollama pull nomic-embed-text && ollama pull llama3.2:3b"

Brain CMS ??

A neuroscience-inspired memory architecture for OpenClaw agents. Replaces flat file injection with sparse, semantic, frequency-gated memory loading.

What This Installs

memory/
├── INDEX.md          ← Hippocampus: topic router + cross-links
├── ANCHORS.md        ← Permanent high-significance event store
└── schemas/          ← Domain-specific semantic schemas (you create these)

memory_brain/
├── index_memory.py   ← Embeds schemas into LanceDB vector store
├── query_memory.py   ← Semantic similarity search
├── nrem.py           ← NREM sleep cycle (compression + anchor promotion)
├── rem.py            ← REM sleep cycle (LLM consolidation via Ollama)
└── vectorstore/      ← LanceDB database (auto-created)

Setup (one-time)

# 1. Run the installer
python3 ~/.openclaw/workspace/skills/brain-cms/install.py

# 2. Index your schemas
cd ~/.openclaw/workspace/memory_brain
.venv/bin/python3 index_memory.py

# 3. Test retrieval
.venv/bin/python3 query_memory.py "your topic here" --sources-only

How It Works

Boot sequence: Load MEMORY.md (lean core) + today's daily log. Nothing else.

When a topic appears: Read memory/INDEX.md → load only the relevant schemas (spreading activation). Check memory/ANCHORS.md for high-significance events.

For ambiguous topics: Run semantic search:

memory_brain/.venv/bin/python3 memory_brain/query_memory.py "message text" --sources-only

Auto-schema creation: When a new significant project or domain appears:

1. Create memory/.md
2. Add to INDEX.md with triggers + priority + cross-links
3. Re-index: memory_brain/.venv/bin/python3 memory_brain/index_memory.py

Sleep cycles:

# NREM — run on shutdown (~30s, no LLM)
cd ~/.openclaw/workspace/memory_brain && .venv/bin/python3 nrem.py

# REM — run weekly (2-5 min, uses local llama3.2:3b, free)
cd ~/.openclaw/workspace/memory_brain && .venv/bin/python3 rem.py

Memory Layers (CMS)

Tagging Anchors

In any daily log, tag high-significance events:

[ANCHOR] Major demo success — full pipeline working end-to-end

NREM auto-promotes these to ANCHORS.md on next shutdown.

Token Savings

Typical MEMORY.md: 150-300 lines injected every session. With Brain CMS: ~50-line core + schemas loaded only when relevant. Estimated savings: 40-60% reduction in context tokens per session.

Requirements

• Python 3.10+
• Ollama (for embeddings + REM consolidation)
• 500MB+ storage for vector store and models
• lancedb, numpy, pyarrow, requests (auto-installed)