A comprehensive long-term memory framework for AI agents featuring Markdown-based storage, semantic search, and structured feedback loops.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install enhanced-memory-4types
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 enhanced-memory-4types 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 System?
The Memory System is a robust persistent storage layer designed to give AI agents a long-term memory without the complexity of a dedicated database. By utilizing a local Markdown-based file system, it ensures that your agent's knowledge is human-readable, easily editable, and simple to back up. It is a core component of the Openclaw Skills ecosystem, enabling agents to remember user preferences, project details, and specific technical feedback over long periods.
This skill intelligently manages context by categorizing information into four distinct types: user, feedback, project, and reference. It also includes an automated Memory Flush mechanism that saves context to the file system when token limits are approached, preventing critical information loss during long sessions.
Memory System Use Cases
- Preserving developer preferences and technical background (e.g., years of experience in specific languages).
- Implementing bidirectional feedback loops to record both positive affirmations and corrective instructions.
- Managing project-specific knowledge such as milestones, active contributors, and architectural decisions.
- Storing external resource pointers like API documentation links, monitoring dashboards, and bug trackers.
How Memory System Works
- The system automatically loads relevant memories from the local directory at the start of a session.
- During the conversation, the agent identifies key information and classifies it into one of the four memory categories.
- The agent uses memory_write to persist data as Markdown files, ensuring portability and transparency.
- When the conversation context nears the token threshold, the Memory Flush mechanism triggers an automatic persistence routine.
- For retrieval, the system performs a semantic search via Ollama (if configured) or falls back to keyword matching to pull relevant context back into the prompt.
Memory System Setup
Install the memory-system via the Openclaw Skills manager:
clawhub install memory-system
To enable semantic vector search, ensure Ollama is installed and pull the required embedding model:
ollama pull nomic-embed-text
Memory System Data Schema & Taxonomy
The system organizes data in a hierarchical Markdown structure within the defined memory directory:
| Directory | Memory Type | Description |
|---|---|---|
/user |
User | Personal details, goals, and skill levels. |
/feedback |
Feedback | Positive and negative corrections with 'Why' and 'How' metadata. |
/project |
Project | Status updates, deadlines, and project-specific logic. |
/reference |
Reference | External links, system pointers, and resource locations. |
MEMORY.md |
Index | A root index file acting as the entry point for all stored memories. |
Memory System Advanced Features
- Bidirectional Feedback Recording: Distinct tracking for positive and negative reinforcement to refine agent behavior.
- Context Safeguard: Automated token-aware flushing to prevent memory loss in high-volume sessions.
- Vector-Enabled Semantic Search: Integration with Ollama for deep-context retrieval beyond simple keyword matching.
- Group Isolation: Support for multi-group environments where memory remains private and independent between different teams or projects.
SKILL.md
Loading
Related Openclaw Skills
Work Report Summary
A structured tool for persisting work logs in a local SQLite database to generate precise daily and weekly progress summaries.
Memory System
A sophisticated file-based memory architecture for AI agents that combines semantic search with categorized persistent storage for long-term context retention.
Memory System
A comprehensive memory architecture for AI agents featuring tiered storage, semantic vector search, and automated memory consolidation.
Spring Fountain Revival
A robust memory survival and triple-layer backup system designed to ensure AI agent interaction data never disappears.
Axios Malware Scanner
A specialized security diagnostic tool to identify and mitigate the 2026 axios supply-chain attack on local development environments.
Creem Agent
An autonomous store operations manager that monitors SaaS health, manages failed payments, and handles churn winbacks for Creem.io merchants.
Featured*
