A sophisticated Retrieval-Augmented Generation (RAG) system that uses SQLite and vector embeddings to give your AI agent a persistent, semantic memory.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install oee-knowledge-base
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 oee-knowledge-base 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 Knowledge Base (RAG) — Your Second Brain?
The Knowledge Base (RAG) skill, developed by Odin's Eye Enterprises, acts as a high-performance second brain for your AI agent. It allows users to ingest text, URLs, and files into a local SQLite database, which then becomes searchable through semantic embeddings. This ensures that your agent can recall information based on meaning rather than just keywords, providing a powerful memory layer for any workflow.
By integrating these Openclaw Skills, developers can bridge the gap between ancient wisdom and modern intelligence. The system provides a robust architecture for managing unstructured data, making it an essential tool for those looking to build more context-aware and capable AI agents that never forget important details.
Knowledge Base (RAG) — Your Second Brain Use Cases
- Storing meeting notes and insights for future semantic recall during project planning.
- Indexing local documentation and markdown files to provide a technical context for coding agents.
- Creating a persistent long-term memory for AI agents to track user preferences and historical data.
- Performing deep semantic searches across large collections of saved notes to find relevant information quickly.
How Knowledge Base (RAG) — Your Second Brain Works
- Data Ingestion: Users provide text, files, or URLs via the ingest script to add content to the database.
- Embedding Generation: The system uses either Anthropic or OpenAI APIs to generate vector embeddings for the input data.
- Storage: The content and its corresponding embeddings are stored in a local SQLite database (kb.db).
- Semantic Querying: When a user or agent asks a question, the system converts the query into an embedding and performs a similarity search.
- Context Retrieval: The most relevant pieces of information are retrieved and provided as context for the agent's response.
Knowledge Base (RAG) — Your Second Brain Setup
To get started with these Openclaw Skills, ensure you have Python 3.10+ and the necessary API keys.
# Set your preferred API key
export ANTHROPIC_API_KEY="your_api_key"
# OR
export OPENAI_API_KEY="your_api_key"
# The system will automatically create kb.db upon first ingestion
python ingest.py "Example note to remember."
Knowledge Base (RAG) — Your Second Brain Data Schema & Taxonomy
The Knowledge Base skill organizes its data within a local SQLite structure for maximum portability and speed.
| Component | Purpose |
|---|---|
| kb.py | The core engine handling embeddings, storage logic, and retrieval algorithms. |
| ingest.py | CLI utility for importing text and files into the Knowledge Base. |
| query.py | CLI utility for executing semantic searches and context retrieval. |
| kb.db | The auto-created SQLite database file containing all notes and vector data. |
Knowledge Base (RAG) — Your Second Brain Advanced Features
- Support for multi-provider embeddings using either OpenAI or Anthropic models.
- File-based batch ingestion allowing for the rapid indexing of entire document folders.
- Semantic search capabilities that understand the intent and context of queries beyond keyword matching.
- Lightweight and self-hosted design requiring no external managed database services.
- Specialized CLI triggers for agents to automatically save and retrieve context during active sessions.
SKILL.md
Loading
Related Openclaw Skills
CRM Intelligence
A sophisticated 2-stage AI filtering and scoring engine designed to optimize personal CRM management.
Humanizer AI Content De-Robotifier
A specialized utility that strips AI patterns and robotic language from text to create authentic, human-like content for any platform.
AI Cost Tracker
A comprehensive tool for logging API calls and analyzing AI expenditure to optimize model costs.
elizaOS Cloud
Deploy, manage, and scale intelligent AI agents with full elizaOS Cloud API integration for multimodal content and containerized workflows.
Social Research (Ravens)
A tiered social intelligence tool that gathers X/Twitter insights through API access, web search, and browser scraping.
Announcer
House-wide text-to-speech announcements using AirPlay speakers, Airfoil, and ElevenLabs.
Featured*
