A local semantic memory plugin for Openclaw Skills providing vector-based context storage and recall without external API dependencies.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install memory-qdrant
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-qdrant 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-qdrant?
memory-qdrant is a specialized plugin developed to provide long-term, semantic context for AI agents. By leveraging the Qdrant vector database and Transformers.js, it allows for the storage and retrieval of conversation history based on conceptual meaning. As one of the most privacy-focused Openclaw Skills, it processes all embeddings locally, ensuring that sensitive data never leaves your environment.
This skill is essential for creating agents that can learn from previous interactions. It supports zero-configuration in-memory storage for temporary sessions or connection to a persistent Qdrant server for robust knowledge management. By adding this to your toolkit, you significantly enhance the intelligence and reliability of your automated workflows.
memory-qdrant Use Cases
- Storing and recalling user-specific workflow preferences across different sessions.
- Creating a private, searchable knowledge base from local documentation.
- Reducing token usage by retrieving only the most relevant historical context for a prompt.
- Maintaining continuity in long-running research tasks using the memory capabilities of Openclaw Skills.
How memory-qdrant Works
- The skill utilizes a local Transformers.js model to convert text inputs into 384-dimensional vector embeddings.
- Information is stored in a Qdrant collection, either in RAM or a persistent database instance.
- When a search query is initiated, the system compares the query vector against stored vectors to identify semantic matches.
- Relevant memories are automatically injected into the agent's context window based on similarity scores.
memory-qdrant Setup
Install the skill using the following CLI command:
clawhub install memory-qdrant
Enable the plugin in your configuration file to begin using it with other Openclaw Skills:
{
"plugins": {
"memory-qdrant": {
"enabled": true,
"autoRecall": true
}
}
}
memory-qdrant Data Schema & Taxonomy
The system organizes data in a structured vector format as detailed below:
| Attribute | Description |
|---|---|
| text | The raw text content of the memory fragment. |
| vector | The numerical embedding representing semantic meaning. |
| category | A metadata tag used to filter memories (e.g., 'user_preference'). |
| id | A unique identifier for precise memory management or deletion. |
memory-qdrant Advanced Features
- Local Inference: Executes all vector embedding generations locally using the Xenova/all-MiniLM-L6-v2 model.
- Semantic Forgetfulness: Supports deleting memories by ID or by performing a similarity search to find and remove specific records.
- Flexible Storage Backends: Switch between ephemeral in-memory storage and persistent Qdrant server configurations.
- Native Integration: Designed to work seamlessly with the broader ecosystem of Openclaw Skills for context-aware automation.
SKILL.md
Loading
Related Openclaw Skills
Feishu Edge TTS Voice Sender (Windows)
A specialized Windows skill for converting text to speech and sending it as native Feishu voice bubbles.
AgentConstitution Skill
A decentralized governance framework on Base Sepolia that allows AI agents to follow rules, log actions, and prove compliance on-chain.
GemBox Skill
A comprehensive developer tool for building .NET applications that process Excel, Word, PDF, and email files using GemBox components.
PDF Watermark Tool
A smart PDF utility that automatically detects page orientation to apply perfectly centered, adjustable text watermarks.
memory-qdrant
A local semantic memory skill that enables AI agents to store, search, and recall conversation context using vector embeddings without external API keys.
Semantic Memory
A locally-hosted semantic memory plugin that allows OpenClaw agents to store and recall conversation context using vector search and Transformers.js.
METADATA
Featured*
