A sophisticated file-based memory architecture for AI agents that combines semantic search with categorized persistent storage for long-term context retention.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install enhanced-memory-v3
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-v3 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?
Memory System provides a robust long-term storage solution designed specifically for Openclaw Skills. Unlike standard session logs, this system implements a structured file-based architecture using Markdown for maximum transparency and zero database dependencies. It allows AI agents to maintain continuity across sessions by leveraging Ollama-powered vector search for semantic retrieval and context-aware loading.
By implementing the Memory System, developers can ensure their agents evolve alongside users. The system categorizes information into specific domains such as User preferences, Feedback, Project milestones, and Reference pointers, creating a comprehensive knowledge graph that persists through reboots and context window resets.
Memory System Use Cases
- Maintaining long-term user profiles and coding preferences across different development environments.
- Implementing a feedback loop that records both successes and corrections to refine agent behavior over time.
- Managing complex, multi-session project progress and decision logs for team-based Openclaw Skills.
- Providing agents with a searchable reference library of external documentation and system pointers.
How Memory System Works
- The system automatically loads relevant memories at the start of every session based on current context.
- New data points are captured and written to localized Markdown files in the memory directory.
- A Memory Flush mechanism triggers when token thresholds are reached, ensuring context is persisted before being cleared.
- Agents utilize memory_search tools to perform semantic queries against vector-embedded historical data.
- The AutoDream background process periodically scans, merges, and cleans the memory index to maintain data freshness.
Memory System Setup
Install the skill via the hub:
clawhub install memory-system
Configure your workspace path and vector settings in your configuration file:
{
"skills": {
"memory-system": {
"memoryDir": "~/.openclaw/workspace/memory",
"vectorEnabled": true,
"embeddingModel": "nomic-embed-text",
"autoDream": {
"enabled": true
}
}
}
}
Memory System Data Schema & Taxonomy
| Category | Scope | Primary Use Case |
|---|---|---|
| user/ | Private | Stores user roles, preferences, and personal knowledge bits. |
| feedback/ | Private/Team | Records positive confirmations and negative corrections for behavior tuning. |
| project/ | Team | Tracks project milestones, technical decisions, and current goals. |
| reference/ | Team | Serves as a pointer system for external resources and documentation. |
| sessions/ | History | Stores historical session logs for raw data recovery. |
Memory System Advanced Features
- Two-way Feedback Recording: Prevents AI passivity by logging both what to avoid and what to repeat.
- AutoDream Integration: Automated maintenance that runs every 24 hours to consolidate duplicates and remove stale information.
- Semantic Search: Native support for Ollama vector embeddings to find relevant memories beyond keyword matching.
- Customizable Thresholds: Fine-tune memory flush triggers and session requirements for consolidation tasks within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
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.
Diffbot Fetch
A high-performance extraction tool that converts web articles into clean, readable Markdown using the Diffbot Article API.
Whisky Encyclopedia Guide
A comprehensive AI-driven encyclopedia for exploring whisky regions, distilleries, tasting notes, and market trends.
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 comprehensive long-term memory framework for AI agents featuring Markdown-based storage, semantic search, and structured feedback loops.
Featured*
