An intelligent, modular memory system for AI agents that integrates semantic search, multi-provider embeddings, and Flomo notes.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install memory-core-ng
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 memory-core-ng 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 Memory Core?
Memory Core is a sophisticated, modular memory engine designed to provide AI agents with a long-term, searchable knowledge base. By leveraging the framework of Openclaw Skills, this tool enables developers to implement semantic search capabilities using a variety of embedding and reranker providers, including OpenAI, Edgefn, or local models. It serves as a bridge between raw information and actionable intelligence, ensuring that agents can recall relevant context across sessions.
The system is built with flexibility in mind, allowing for seamless integration into existing workflows. One of its standout features is the native support for Flomo notes, which allows users to transform their personal observations and captures into a structured, queryable resource that any agent utilizing Openclaw Skills can access and understand.
Memory Core Use Cases
- Providing long-term context and retrieval-augmented generation (RAG) for AI chat sessions.
- Importing and indexing personal knowledge from Flomo notes for quick retrieval.
- Building custom local or cloud-based knowledge repositories for specialized AI tasks.
- Enhancing search precision through intelligent reranking of vector search results.
How Memory Core Works
- Initialize the Memory Core through the standard Openclaw Skills integration path.
- Configure your preferred embedding provider and reranker within the global settings.
- Add new memories or bulk-import existing data, such as Flomo backup files, into the vector store.
- Perform semantic search queries using the CLI or programmatic API to retrieve the most relevant data fragments.
- Apply the reranker module to refine the search results, ensuring the highest quality context is delivered to the AI.
Memory Core Setup
To integrate this into your environment, modify your Openclaw Skills configuration file located at ~/.openclaw/openclaw.json:
{
"skills": {
"memory-core": {
"enabled": true,
"config": { "apiKey": "sk-your-key" }
"
}
}
}
For programmatic usage in your own scripts:
const { quickStart } = require('./index');
const memoryCore = await quickStart({ apiKey: 'your-key' });
const result = await memoryCore.search('your query content');
Memory Core Data Schema & Taxonomy
| Component | Description |
|---|---|
| Embeddings | Support for Edgefn, OpenAI, and local vector generation models. |
| Reranker | An intelligent scoring layer used to optimize the relevance of search results. |
| Flomo Integration | Dedicated logic for parsing and importing Flomo .zip or .json backup files. |
| Commands | CLI-based interface for operations like search, add, stats, and import. |
| Storage | Organized modular architecture with clear separation between core logic, config, and tests. |
Memory Core Advanced Features
- Multi-platform embedding support allowing users to switch between cloud and local providers.
- Integrated semantic reranking to significantly improve RAG accuracy for complex queries.
- Comprehensive CLI management toolset for searching, adding, and monitoring memory statistics.
- Specialized Flomo import tool to synchronize personal knowledge management with Openclaw Skills.
- Modular architecture that supports easy extension for new vector databases or data sources.
SKILL.md
Loading
Related Openclaw Skills
Superdesign
A specialized design agent that automates frontend UI/UX workflows, from initial repo analysis to component extraction.
My Generate QR Code
An AI-powered utility for generating highly customizable QR codes and barcodes for various data types including URLs and WiFi configurations.
Folder Inspector
A high-performance AI agent skill for scanning local directories and auditing file metadata using absolute paths.
BVG Route Planner
A comprehensive tool for real-time Berlin public transport routing and departure information using the BVG API.
Smart Memory System
A Retrieval-Augmented Generation (RAG) based intelligence system providing semantic search and memory optimization for Openclaw Skills.
Humanizer
A sophisticated writing editor that identifies and removes common AI-generated signatures to create natural, human-sounding text.
Featured*
