memory-lancedb-pro

Configure LanceDB-backed persistent memory with hybrid retrieval for OpenClaw agents.

Updated Mar 17, 2026

Search Tags:#mcp #retrieval #memory #governance #persistence #lancedb #openclaw

Ready to run

npx skills add https://github.com/M1Albert/xiaoman-openclaw-skills --skill memory-lancedb-pro-m1albert

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-lancedb-pro
Source: https://github.com/M1Albert/xiaoman-openclaw-skills/tree/main/memory-lancedb-pro-skill
Command: npx skills add https://github.com/M1Albert/xiaoman-openclaw-skills --skill memory-lancedb-pro-m1albert

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

OpenClaw lacks a robust, persistent memory layer; memory-lancedb-pro provides production-grade long-term memory integration with LanceDB, enabling durable memory storage, hybrid retrieval, and governance for memory tools.

Core Features & Use Cases

Persistent memory storage with LanceDB (embedded, no server)
Hybrid vector + BM25 retrieval for recall accuracy
LLM-powered Smart Extraction, Weibull decay lifecycle, and multi-scope isolation
Full MCP memory tool support: memory_recall, memory_store, memory_forget, memory_update, memory_stats, memory_list, self_improvement_log, self_improvement_extract_skill, self_improvement_review
Use cases include configuring memory in OpenClaw workflows, cross-scope memory management, and governance of self-improvement processes

Quick Start

To begin, place memory-lancedb-pro in your OpenClaw workspace skills directory and run through the installation and configuration steps described in the included SKILL.md.

Frequently Asked Questions about memory-lancedb-pro

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I add persistent long-term memory to OpenClaw agents?▼

Persistent long-term memory for OpenClaw agents requires LanceDB-backed storage to retain data across sessions. This enables durable memory storage, hybrid retrieval, and self-improvement governance for workflows.

What is hybrid retrieval for agent memory and how does it improve recall?▼

Hybrid retrieval combines vector embeddings with BM25 keyword scoring to improve recall accuracy for agent memory. This mechanism ensures relevant context is matched using both semantic similarity and exact term frequency.

How do I configure multi-scope memory isolation for OpenClaw workflows?▼

Multi-scope memory isolation for OpenClaw workflows is configured through LanceDB storage boundaries and MCP memory tools. This separates memory contexts across different agents or scopes using explicit validation checks.

Does LanceDB work as an embedded memory store without a separate server?▼

LanceDB functions as an embedded memory store without requiring a separate server setup. This embedded architecture allows direct integration for persistent agent memory within the OpenClaw workspace.

How does Weibull decay lifecycle management work for agent memory?▼

Weibull decay lifecycle management applies a statistical decay function to agent memory entries over time. This governance mechanism automatically degrades the relevance of outdated memories to maintain efficient storage and recall.

What MCP memory tools are supported for cross-scope memory management?▼

MCP memory tools supported include memory_recall, memory_store, memory_forget, memory_update, memory_stats, memory_list, and self_improvement functions. These tools manage cross-scope memory with explicit safety and validation checks.