A comprehensive developer toolkit for scaffolding, sanitizing, and distributing reusable multi-agent memory architectures.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-memory-kit
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install openclaw-memory-kit using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OpenClaw Memory Kit?
OpenClaw Memory Kit is a specialized framework designed to streamline the creation and sharing of complex memory systems for AI agents. It provides a robust architecture for multi-agent collaboration, featuring role-based prompts, task-board conventions, and pre-configured startup scripts. By leveraging Openclaw Skills like this one, developers can ensure their agentic workspaces are consistent, scalable, and ready for team collaboration.
The kit excels at portability and security. It allows users to package existing memory setups while automatically stripping away private environment variables and sensitive configuration details. Whether you are bootstrapping a fresh workspace or turning a local framework into a distributable asset, this kit provides the necessary automation to maintain high standards in the Openclaw Skills community.
OpenClaw Memory Kit Use Cases
- Bootstrapping a new multi-agent workspace with pre-defined memory-lancedb-pro configurations.
- Sanitizing private memory setups to share with teammates or the public without leaking credentials.
- Creating distributable versions of custom AI frameworks to be listed as Openclaw Skills.
- Standardizing role prompts and collaboration documents across different development environments.
- Setting up local gateways with consistent port mappings and model defaults.
How OpenClaw Memory Kit Works
- The user defines a target root directory and specifies primary model defaults and gateway ports.
- The system runs a PowerShell bootstrap script to generate a structured workspace including configuration files and launcher scripts.
- It installs critical dependencies like memory-lancedb-pro locally to ensure plugin-sdk resolution is maintained.
- A sanitization pass replaces private data such as app IDs and filesystem usernames with placeholders.
- The tool generates a suite of collaboration documents, task boards, and role-specific directories.
- Finally, it provides human-facing handoff documentation to help new users or teammates onboard to the shared kit.
OpenClaw Memory Kit Setup
To initialize the workspace and install the core components of these Openclaw Skills, run the following command in PowerShell:
& "scripts/bootstrap-openclaw-memory.ps1" `
-TargetRoot "$HOME/.openclaw-memory-kit" `
-PrimaryModel "minimax/M2.5" `
-GatewayPort 18789
To overwrite an existing configuration, add the -Force flag. If you prefer to handle plugin installation manually later, use the -SkipCorePluginInstall parameter.
OpenClaw Memory Kit Data Schema & Taxonomy
The kit organizes data into a clean, predictable hierarchy to maintain compatibility across Openclaw Skills:
| File/Folder | Description |
|---|---|
openclaw.json |
The primary configuration file for plugin paths and slots. |
workspace/agents/ |
Contains sub-directories for each specific agent role and their prompts. |
workspace/shared/ |
Shared documents for the task system and memory collaboration. |
.env.example |
Template for environment variables and API keys. |
start-gateway.ps1 |
Launcher script for the local memory gateway. |
plugins.load.paths |
Defines where the memory-lancedb-pro plugin is located. |
OpenClaw Memory Kit Advanced Features
- Role Catalog Customization: Easily modify the
New-RoleCatalogfunction to define custom agent personas. - Isolated State Management: Defaults to isolated target roots to prevent conflicts with global OpenClaw configurations.
- Flexible Integration: Treats Feishu, Telegram, and WeChat as optional modules that can be prewired or added later.
- Automated Sanitization: Integrated logic to ensure private LAN addresses and personal scope names are never exported in shared Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
PC Operation Security (PC-OCS)
An impact-based security classification tool designed to assess risks, assign safety levels, and provide audit guidelines for personal computer operations.
Kimi Code API Integration
A specialized integration guide and configuration skill to run Kimi K2.5 as a drop-in replacement for Anthropic models in OpenClaw and Claude Code.
WeChat Publisher Setup Agent Team
Deploy a specialized AI agent team to automate visual design, layout beautification, and API-based publishing for WeChat Official Accounts.
Onfleet
A powerful integration for Onfleet that enables AI agents to manage organizations, track deliveries, and optimize last-mile logistics operations.
cuihua-dependency-updater
An AI-powered dependency assistant that intelligently manages npm and yarn package updates with automated safety checks and breaking change detection.
SLS Trace Analysis: Alibaba Cloud Logging & ARMS Debugger
A comprehensive full-link troubleshooting skill that integrates Alibaba Cloud SLS logs, ARMS call chains, source code analysis, and database diagnostics.
Featured*
