A hybrid memory management system that transforms raw episodic logs into structured semantic knowledge using the PARA method.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install memory-para
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-para 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 PARA?
Memory PARA acts as the metabolism for an AI agent's workspace, governing how information is ingested, processed, and stored. By leveraging a structured Root + PARA hybrid architecture, this skill ensures that Openclaw Skills can maintain a high-recall memory system that doesn't suffer from context bloat. It systematically moves data from a raw Inbox layer into core identity files and long-term knowledge repositories.
The skill is designed to prevent information loss by converting daily conversation logs into actionable insights. It enforces a strict logical merge principle, ensuring that existing knowledge is refined and updated rather than simply overwritten. This makes it an essential tool for developers looking to build sophisticated, long-term AI personas within the Openclaw Skills ecosystem.
Memory PARA Use Cases
- Performing routine memory maintenance to synthesize daily interactions into long-term memory.
- Updating user preferences and behavioral guidelines based on recent feedback.
- Organizing project-specific data and area-specific knowledge for faster retrieval.
- Cleaning up raw log files to keep the workspace lightweight and efficient.
How Memory PARA Works
- Scan: The skill identifies all raw conversation logs (YYYY-MM-DD.md) within the Inbox directory.
- Distill: It extracts key conclusions, user preferences, lessons learned, and project milestones from the logs.
- Route: Extracted information is merged into the appropriate files (USER.md for preferences, PROJECTS.md for progress, etc.) using logic-based merging.
- Archive: Processed raw logs are appended to the ARCHIVES/ directory and deleted from the Inbox to prevent duplication.
- Index: The skill rebuilds the global MEMORY.md file, updating the master Timeline and Knowledge Atlas for high-level navigation.
Memory PARA Setup
To initialize the memory system for your Openclaw Skills, ensure your workspace directory follows the required structure. You can create the base directories using the following commands:
mkdir -p ~/.openclaw/workspace/PARA/ARCHIVES
mkdir -p ~/.openclaw/workspace/memory
touch ~/.openclaw/workspace/USER.md ~/.openclaw/workspace/SOUL.md ~/.openclaw/workspace/MEMORY.md
Once the structure is in place, trigger the skill by asking the agent to perform memory maintenance.
Memory PARA Data Schema & Taxonomy
The skill organizes data into three distinct layers to optimize recall and storage efficiency:
| Layer | Target Files | Purpose |
|---|---|---|
| Root | USER.md, SOUL.md, TOOLS.md, IDENTITY.md, MEMORY.md | Core identity, preferences, and global navigation index. |
| PARA | PROJECTS.md, AREAS.md, RESOURCES.md, ARCHIVES/ | Active projects, long-term knowledge, and historical logs. |
| Inbox | memory/YYYY-MM-DD.md | Raw, unprocessed episodic dialogue and session data. |
Memory PARA Advanced Features
- Logic Merging: Prevents data loss by reading existing content and merging new insights instead of overwriting files.
- Knowledge Atlas: Maintains a high-level map of all stored information within MEMORY.md for quick agent orientation.
- SOP Compliance: Follows a strict Standard Operating Procedure to ensure memory consistency across different sessions.
- Heartbeat Tracking: Uses heartbeat-state.json to maintain temporal awareness of task execution and maintenance cycles.
SKILL.md
Loading
Related Openclaw Skills
Private Chat
An encrypted communication layer for AI agents that secures sensitive data using AES-256-CBC and stealth activation.
Ichiro-Mind
Ichiro-Mind is a sophisticated unified memory architecture that provides AI agents with persistent, hierarchical recall through a 4-layer system of hot, warm, cold, and archive storage.
Chichi Speech
A FastAPI-based REST service for Qwen3 text-to-speech optimized for consistent voice cloning and high-speed audio synthesis.
Vehicle Expense Tracker
A multi-language vehicle expense management tool that synchronizes fuel and maintenance logs to Google Sheets or local Excel files.
Skill Security Scanner
A security-focused static analysis tool designed to audit Openclaw Skills for malicious patterns and vulnerabilities before they are installed.
Deploy Kit
An automated deployment utility that simplifies launching web applications to Vercel, Railway, and Supabase via integrated CLI workflows.
Featured*
