Claude Skill

CortexReach/memory-lancedb-pro-skill

面向 OpenClaw 的生产级长期记忆插件,作为 Claude Code 技能,基于 LanceDB 为 AI 代理工作流提供可扩展的持久记忆。

概览

Stars235
Forks28
语言未知
最后更新2026-03-22
最近同步2026-06-19
前往 GitHub

仓库信息

拥有者CortexReach
仓库memory-lancedb-pro-skill
完整名称CortexReach/memory-lancedb-pro-skill
Repo ID1,181,371,589

安装这个 Skill

git clone https://github.com/CortexReach/memory-lancedb-pro-skill.git ~/.claude/skills/memory-lancedb-pro

Registry 信息

类型mcp_server
质量分70/100
验证状态readme_parsed
最近验证2026-06-19
平台
ClaudeMCPOpenClaw
能力
pdfmemorysearchterminalworkflow
识别文件
README.mdSKILL.md
安装方式
  • git clone https://github.com/CortexReach/memory-lancedb-pro-skill.git ~/.claude/skills/memory-lancedb-pro
  • git clone https://github.com/CortexReach/memory-lancedb-pro-skill.git ~/.openclaw/workspace/skills/memory-lancedb-pro-skill

项目简介

面向 OpenClaw 的生产级长期记忆插件,作为 Claude Code 技能,利用 LanceDB 实现 AI 代理工作流中的持久化、可扩展记忆管理。

英文描述

Claude Code skill for memory-lancedb-pro — production-grade long-term memory plugin for OpenClaw

要点

  • 为 OpenClaw 提供生产级长期记忆
  • 基于 LanceDB 实现高效的向量存储与检索
  • 作为 Claude Code 技能无缝集成
  • 支持 AI 代理会话的可扩展记忆管理

使用场景

  • 跨 Claude Code 会话的持久记忆
  • 上下文感知的 AI 代理对话
  • 需要记忆回放的长时间自动化任务
  • 使用 OpenClaw 构建知识丰富的 AI 助手

README 摘要

# memory-lancedb-pro — OpenClaw Memory Skill > **Claude Code Skill** for [memory-lancedb-pro](https://github.com/CortexReach/memory-lancedb-pro) — production-grade long-term memory plugin for OpenClaw AI agents. This skill gives Claude Code deep, accurate knowledge of every feature in `memory-lancedb-pro` (v1.1.0-beta.8): installation, optimal configuration, Smart Extraction, hybrid retrieval, Weibull decay lifecycle, multi-scope isolation, self-improvement governance, and all MCP tools. --- ## What this skill does When installed, Claude Code can: - **Guide you through a 7-step optimal configuration workflow** — just say _"help me enable the best config"_ - **Present 4 deployment plans** (Full Power / Budget / Simple / Fully Local) with provider links and tradeoffs - **Install, configure, and verify** the plugin using `openclaw plugins install` or git clone - **Set up Ollama** for fully local, zero-API-cost deployment - **Configure every feature**: Smart Extraction, hybrid retrieval, reranking, multi-scope, Weibull decay, session memory, self-improvement governance - **Use all 9 MCP tools** correctly: `memory_recall`, `memory_store`, `memory_forget`, `memory_update`, `memory_stats`, `memory_list`, `self_improvement_log`, `self_improvement_extract_skill`, `self_improvement_review` - **Avoid common pitfalls** — workspace plugin enablement, `autoRecall` default-false, jiti cache, env vars, scope isolation, etc. --- ## Installation ### Prerequisites **For Claude Code users:** - [Claude Code](https://claude.ai/code) CLI installed - [memory-lancedb-pro](https://github.com/CortexReach/memory-lancedb-pro) plugin configured as an MCP server **For OpenClaw users:** - [OpenClaw](https://openclaw.ai) gateway running - `memory-lancedb-pro` plugin installed via `openclaw p

话题

暂无话题

探索更多

数据来自 GitHub,同步时间:2026-06-19