A sophisticated long-term memory plugin for OpenClaw agents that automates fact extraction and contextual recall.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install mem0-config
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 mem0-config 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-mem0?
openclaw-mem0 is a specialized extension designed to provide OpenClaw agents with a persistent memory layer. By integrating Mem0, this skill enables agents to remember user preferences, past interactions, and critical data across different sessions. It is a vital component of the Openclaw Skills ecosystem for anyone building advanced, context-aware AI assistants that need more than just a short-term context window.
This skill supports both a cloud-based platform mode for ease of use and a fully open-source, self-hosted mode for maximum privacy and control. It bridges the gap between ephemeral chat history and a permanent knowledge base, ensuring your agents grow smarter with every interaction.
openclaw-mem0 Use Cases
- Creating personalized AI assistants that remember user history and preferences.
- Building research agents that accumulate knowledge over multiple tasks.
- Reducing token usage by selectively injecting only relevant long-term context.
- Implementing private, self-hosted memory systems using local vector stores like Qdrant.
- Auditing and managing agent knowledge through a dedicated CLI for developers.
How openclaw-mem0 Works
- The plugin monitors agent turns to capture and extract new facts automatically.
- Extracted facts are processed through an embedder and stored in a vector database.
- At the start of a new interaction, the system performs a semantic search based on the current user query.
- Relevant memories are automatically injected into the agent's prompt context before the turn begins.
- Agents can also utilize specialized tools to manually search, store, or delete information during a session.
openclaw-mem0 Setup
Install the plugin using the standard Openclaw Skills CLI:
openclaw plugins install @mem0/openclaw-mem0
For open-source deployments, ensure your local dependencies are running:
# Install and start Ollama
brew install ollama
ollama serve
ollama pull bge-m3:latest
ollama pull llama3.2
# Run Qdrant vector store via Docker
docker run -d -p 6333:6333 qdrant/qdrant
Configure your openclaw.json with either platform or open-source settings and restart the gateway:
openclaw gateway stop && openclaw gateway
openclaw-mem0 Data Schema & Taxonomy
The skill manages data using a combination of vector embeddings and local relational storage. It is critical to use absolute paths for database configuration to ensure stability.
| Component | Type | Purpose |
|---|---|---|
| Vector Store | Qdrant / Mem0 | Stores high-dimensional embeddings for semantic search retrieval |
| history.db | SQLite | Local database for memory lifecycle tracking and audit trails |
| userId | String | Scopes memories to specific users or agents |
| topK | Integer | Determines the number of memories injected per turn |
openclaw-mem0 Advanced Features
- Auto-Recall and Auto-Capture: Fully automated memory management that requires zero agent prompting.
- Semantic CLI: Search and inspect long-term memories directly from the terminal using openclaw mem0 search.
- Agent-Accessible Toolset: Includes 5 built-in tools for fine-grained memory operations like memory_list and memory_forget.
- Multi-Provider Flexibility: Highly configurable OSS block supporting various LLMs and vector stores within the Openclaw Skills framework.
SKILL.md
Loading
Related Openclaw Skills
A2A Manager
A centralized orchestration layer for managing agent-to-agent communication, Discord environments, and Notion-based task workflows.
subwayskill
A CLI tool for fetching real-time NYC subway departure times and schedules directly within your AI agent environment.
UX/UI Specialist
A professional AI design consultant that analyzes web and mobile interfaces for usability, accessibility, and platform compliance.
POST AI Automation
A powerful automation tool that transforms a single product image into dozens of platform-ready TikTok and Instagram videos with AI voice-overs.
Agent Heartbeat
A configuration-driven mechanism to ensure AI agents maintain online status and perform periodic maintenance tasks automatically.
Absurdist Play
A meta-skill that trains AI agents to move beyond transactional responses toward genuine, creative, and authentic human connection.
Featured*
