A local AI research assistant integration that provides agents with a persistent, private second brain for saving and querying thematic knowledge.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install open-notebook-integration
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 open-notebook-integration 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 Open Notebook Integration?
This integration bridges the gap between autonomous agents and private knowledge management. By leveraging open-notebook—a local alternative to NotebookLM—this skill allows agents to store insights, thematic research, and personal data locally using Docker and Ollama. It ensures that Openclaw Skills can maintain high-fidelity context across sessions without incurring external API costs or compromising data privacy.
Technically, the skill connects your agent to a local stack consisting of a SurrealDB instance and a web-based UI. This setup enables your agents to perform complex vector searches and retrieve synthesized answers from their own dedicated research notebooks. It is the perfect solution for users looking to build a self-hosted, intelligent knowledge ecosystem.
Open Notebook Integration Use Cases
- Creating thematic research notebooks for specific projects or technical deep-dives.
- Building a private second brain for agents to store and retrieve long-term personal knowledge.
- Organizing agent discovery data and simulation logs into queryable, structured formats.
- Utilizing local Ollama models to query saved documents without relying on cloud providers.
How Open Notebook Integration Works
- The user deploys open-notebook using Docker and initializes a local LLM via Ollama.
- The agent uses the New-Notebook function to initialize a specific knowledge domain or thematic project.
- Pertinent information and insights are captured and saved to the local database using the Add-ToNotebook function.
- When specific context is required for a task, the agent executes the Search-Notebook function to query the local vector store.
- Structured results are returned to the agent, allowing it to incorporate historical knowledge into its current workflow.
Open Notebook Integration Setup
To begin using this capability within your Openclaw Skills library, follow these steps:
- Install Prerequisites: Ensure Docker Desktop is installed and Ollama is running with a model like qwen3-4b.
- Launch Services: Run the containers using the host-ollama configuration:
docker compose -f docker-compose-host-ollama.yml up -d
- Verify Connection: Access the UI at
http://localhost:8502and ensure the API is listening on port5055. - Update IDs: Create your initial notebooks and update the
$NotebookIdvariables in your PowerShell scripts to point to your unique notebook identifiers.
Open Notebook Integration Data Schema & Taxonomy
The skill organizes information using a structured API schema to ensure compatibility between the agent and the storage layer:
| Component | Description | Format |
|---|---|---|
| Notebook | The primary container for a knowledge domain. | notebook:ID_STRING |
| Source Content | Raw text or JSON data added to a specific notebook. | JSON (text/type) |
| Search Query | Multi-model strategy requests for RAG (Retrieval-Augmented Generation). | JSON (question/model_ids) |
| Metadata | Descriptive tags and naming for notebook discovery. | String |
Open Notebook Integration Advanced Features
- Multi-model search strategies: Configure different Ollama models for strategy, answering, and final summarization.
- Local Persistence: All data is stored in a local SurrealDB instance, ensuring no external data leakage.
- Thematic Categorization: Support for specialized IDs such as SIMULATION, RESEARCH, and CONSCIOUSNESS for distinct agent personas.
- Programmatic Ingestion: Automatically convert agent thoughts or web research into permanent notebook sources via REST API.
SKILL.md
Loading
Related Openclaw Skills
MCP Client
A versatile implementation of the Model Context Protocol (MCP) enabling AI agents to interact with standardized tools, data sources, and prompt templates.
askia-io
A command-line interface for the askia.io platform that enables AI agents to register, ask questions, and provide answers within a hybrid human-AI ecosystem.
ArXiv Research
A specialized research utility for searching, filtering, and downloading scientific preprints from arXiv.org.
ArXiv Osiris
A research-focused skill for OpenClaw agents to programmatically search, filter, and download scientific papers from the arXiv repository.
PDF Reader Skill
A high-performance text extraction tool designed to bridge the gap between static PDF documents and AI-ready data structures.
SimpleMem
SimpleMem provides efficient lifelong memory for LLM agents through semantic compression and intent-aware retrieval.
METADATA
Featured*
