A high-performance vector database integration providing semantic persistence and long-term memory for AI agents.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install lancedb-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 lancedb-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 LanceDB Long-Term Memory?
The LanceDB Long-Term Memory skill enables AI agents to maintain a persistent state by leveraging a serverless vector database. Unlike traditional key-value stores, this skill allows for semantic retrieval, meaning agents can find relevant information based on meaning rather than just exact keywords. This is a vital component for building sophisticated Openclaw Skills that require context retention across multiple interactions.
Built on LanceDB, it offers a lightweight yet powerful solution for managing embeddings and metadata. It handles everything from automatic table creation to complex vector similarity searches, ensuring that your agent's memory remains organized, searchable, and scalable.
LanceDB Long-Term Memory Use Cases
- Maintaining user context and preferences across long-term interactions
- Building Retrieval-Augmented Generation (RAG) systems for specialized domains
- Archiving and semantically searching through technical logs or documentation
- Ranking and prioritizing stored information based on importance and category
How LanceDB Long-Term Memory Works
- The skill initializes a connection to a local LanceDB instance and verifies the presence of the memory table.
- When new information is provided, the add_memory function stores the text along with timestamps, categories, and tags.
- For retrieval, the agent uses the search_memories function to perform a vector-based similarity search against the stored content.
- The system filters results by category or importance to refine the context provided to the LLM.
- Continuous updates and statistics tracking ensure the memory remains accurate and high-quality.
LanceDB Long-Term Memory Setup
To integrate this skill into your environment, install the necessary dependencies via pip:
pip install lancedb pandas
Ensure that the storage path (default: ~/clawd/memory/lancedb) is accessible to your agent and that the directory has the appropriate write permissions for Openclaw Skills.
LanceDB Long-Term Memory Data Schema & Taxonomy
| Field | Type | Description |
|---|---|---|
| id | int | Unique primary key for the memory entry |
| timestamp | timestamp | The exact time the memory was recorded |
| content | str | The actual text or data being remembered |
| category | str | Logical grouping (e.g., 'technical', 'personal') |
| tags | list | A list of strings for granular filtering |
| importance | int | A scale (1-10) representing data significance |
| metadata | json | Structured object for additional context-specific data |
LanceDB Long-Term Memory Advanced Features
- Semantic vector search for finding contextually related information rather than keyword matches
- Granular CRUD operations for precise memory management and data cleanup
- Comprehensive storage statistics for monitoring memory growth and distribution across categories
- Support for complex metadata filtering and importance-based ranking to optimize LLM context windows
SKILL.md
Loading
Related Openclaw Skills
Auto-Updater
A daily maintenance utility that ensures your agent and its capabilities are always running the latest stable versions.
McDonald's Helper
An automated MCP skill to manage McDonald's coupons, track promotional calendars, and analyze nutritional data through simple AI commands.
CodeBuddy CLI
CodeBuddy CLI is a Tencent-developed terminal assistant that transforms natural language prompts into executable code and project optimizations.
CodeBuddy CLI
An AI-powered terminal programming assistant from Tencent that enables natural language driven development directly in your shell.
n8n Workflow Management
A specialized toolset for managing, executing, and debugging n8n automation workflows via a powerful REST API interface.
Parallel.ai Search & Research
A high-performance web search API specifically engineered for AI agents to perform deep research with extreme accuracy and structured citations.
Featured*
