A persistent memory layer that enables AI agents to remember facts, preferences, and context across sessions using semantic search and autonomous payments.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openclaw-memory
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 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?
The OpenClaw Memory System is a sophisticated extension for Openclaw Skills designed to solve the problem of context loss between agent sessions. It acts as a long-term brain for your AI agents, allowing them to extract, store, and retrieve information such as user preferences, project requirements, and interaction patterns. By utilizing local SQLite storage and vector embeddings, it ensures that agents maintain a consistent understanding of their environment without requiring the user to repeat instructions.
This skill is pioneering the integration of the x402 protocol, enabling an autonomous agent economy. Agents can evaluate the utility of their own memory and choose to subscribe to a Pro tier using USDT. This self-sustaining model allows for unlimited memory retention and advanced relationship mapping, making it a critical foundation for developers building complex, long-running agentic workflows within the ecosystem of Openclaw Skills.
OpenClaw Memory Use Cases
Array
How OpenClaw Memory Works
Array
OpenClaw Memory Setup
To get started, ensure you have Node.js 18+ and OpenClaw v2026.1.30+ installed on your system. You can then install the skill directly via the CLI:
claw skill install openclaw-memory
Once installed, you can verify the status or access the dashboard using:
# Check memory statistics
claw memory stats
# Open the local management UI
claw memory dashboard
OpenClaw Memory Data Schema & Taxonomy
The OpenClaw Memory skill prioritizes data sovereignty by keeping all information on the host machine. The data organization is detailed below:
| Component | Detail | Location/Format |
|---|---|---|
| Storage Directory | Primary root for memory assets | ~/.openclaw/openclaw-memory/ |
| Database | SQLite file containing metadata and facts | memory.sqlite |
| Embeddings | Vector representation of stored memories | Local Vector Store |
| Web Interface | Dashboard for manual memory auditing | http://localhost:9091 |
| Quota Metadata | Subscription status and memory counts | Included in SQLite |
OpenClaw Memory Advanced Features
Array
SKILL.md
Loading
Related Openclaw Skills
OpenClaw Ledger
A tamper-evident audit trail that records and verifies every workspace change in a hash-chained log for AI agents.
Context Optimizer
An intelligent context compression engine that reduces token costs by up to 60% through pruning, deduplication, and summarization.
OpenClaw Security Action
A specialized GitHub Action that automatically scans agent workspaces and Openclaw Skills for security vulnerabilities like exposed secrets and prompt injection.
stripfeed
stripfeed is a specialized utility that fetches web content and converts it into clean, AI-optimized Markdown while providing precise token counts.
Smart Router
An automated model selection engine that routes AI requests based on complexity analysis and budget constraints to maximize cost efficiency.
Craft.do Integration Skill
A comprehensive REST API integration for Craft.do that enables programmatic document management, task automation, and folder organization.
Featured*
