360 Secure SkillHub
360 安全技能中心

Rewind Memory — Persistent Bio-Inspired Memory for AI Agents

面向 AI Agent 的持久记忆 Skill,采用 L0–L4 分层架构,包含 BM25 关键词检索、知识图谱实体关系与 sqlite-vec 向量相似度,并由编排层做 HybridRAG 多信号融合;提供命令行索引与搜索、会话实时捕获、MCP 服务及 OpenClaw 钩子集成。

vnesin-sarai
vnesin-sarai
热度 31.02
最近更新 2026-04-30 13:37:47
分类:知识依赖:代码执行 / 读写文件 / 第三方 API / MCP 服务应用场景:笔记整理 / 研究 / 工作流 / API 集成

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add rewind-memory
Metadata
name
rewind-memory
description
Persistent, bio-inspired memory for AI agents. 5-layer architecture (L0-L4) with BM25 keyword search, knowledge graph, vector similarity, and HybridRAG fusion. Remembers everything across sessions. Triggers on "agent memory", "persistent memory", "remember across sessions", "rewind memory", "memory search", "knowledge graph", "recall previous".

Rewind Memory — Persistent Memory for AI Agents

Give your agent memory that survives sessions, compactions, and restarts.

What It Does

  • L0 Sensory Buffer — BM25 keyword search over all indexed content
  • L1 System Memory — core files loaded every session
  • L2 Orchestrator — fuses all layers with unified multi-signal scoring
  • L3 Knowledge Graph — entity extraction, relationships, spreading activation
  • L4 Vector Search — semantic similarity via sqlite-vec

Install

pip install rewind-memory

Quick Start

rewind doctor          # auto-diagnose + build index
rewind ingest ./docs/  # index your files
rewind search "what did we decide about auth?"
rewind watch-sessions  # real-time conversation capture

OpenClaw Integration

# Native hook (recommended — survives updates)
rewind-openclaw hook

# Or configure memory_search routing
rewind-openclaw setup

MCP Server

{
  "mcpServers": {
    "rewind": { "command": "rewind-mcp" }
  }
}

6 tools: memory_search, memory_store, memory_extract, memory_stats, memory_feedback, graph_traverse.

Pro Upgrade

Pro adds L5 (communications), L6 (documents), NV-Embed-v2 4096-dim cloud embeddings, cross-encoder reranking, and bio-inspired lifecycle (decay, consolidation, pruning).

pip install rewind-memory-pro

Links

Built by SARAI Defence. Patent pending.