An autonomous research orchestration engine that manages state, synthesis, and verification for Openclaw Skills.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install vaultresearch
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 vaultresearch 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 ResearchVault?
ResearchVault is a sophisticated tool designed to enhance the capabilities of Openclaw Skills by providing a persistent state management layer for complex research tasks. It enables agents to move beyond transient queries by maintaining a local SQLite database known as The Vault, which stores artifacts, findings, and logical links. This infrastructure allows developers and researchers to execute high-velocity data gathering while maintaining a coherent history of discovery.
By integrating seamlessly into the ecosystem of Openclaw Skills, ResearchVault empowers agents to perform divergent reasoning through parallel hypothesis branches. It ensures that data is not just collected but also verified and synthesized, transforming raw information into actionable insights with minimal human intervention. The engine's ability to handle autonomous verification missions makes it a cornerstone for reliable, agentic research workflows.
ResearchVault Use Cases
- Coordinating multi-agent research projects that require persistent data storage and state management.
- Exploring parallel research hypotheses using divergent reasoning branches to compare different outcomes.
- Automated ingestion of multi-source data from URLs, social platforms, and documentation for deep analysis.
- Verifying low-confidence findings through autonomous verification missions to ensure data integrity.
- Enabling cross-agent collaboration via the native Model Context Protocol (MCP) server integration.
How ResearchVault Works
- Initialize a research project with a specific objective to create a localized vault for persistence.
- Ingest data from various sources using the scuttle command to populate the vault with raw artifacts.
- Trigger the synthesis engine to discover and create logical links between findings using local embeddings.
- Execute verification plans where agents identify low-confidence data and autonomously perform secondary checks.
- Access the research state through the MCP server or the Watchdog mode for continuous background monitoring.
ResearchVault Setup
To get started with ResearchVault for your Openclaw Skills, ensure you have Python 3.13 and the uv package manager installed. Use the following commands to initialize your environment:
# Create a virtual environment and install dependencies
uv venv
uv pip install -e .
Once installed, you can initialize your first research vault to begin tracking data:
uv run python scripts/vault.py init --id "research-v1" --name "Project Name" --objective "Define objective"
ResearchVault Data Schema & Taxonomy
ResearchVault organizes information within a structured SQLite database to ensure compatibility with various Openclaw Skills. The schema is optimized for retrieval and relational synthesis.
| Entity | Description | Key Attributes |
|---|---|---|
| Artifacts | Raw data gathered from sources | ID, Source URL, Timestamp, Content |
| Findings | Processed insights extracted from artifacts | Claim, Confidence Score, Evidence Link |
| Links | Semantic relationships between data points | Source ID, Target ID, Relationship Type |
| Branches | Parallel research paths for hypothesis testing | Branch Name, Parent State, Objective |
ResearchVault Advanced Features
- Divergent Reasoning: Create parallel branches to explore multiple hypotheses simultaneously without data collision.
- Synthesis Engine: Automated link discovery that utilizes local vector embeddings to find hidden connections in your research.
- Active Verification: Self-correcting workflows that trigger agents to verify data when confidence scores fall below a set threshold.
- Watchdog Mode: Provides continuous background monitoring of specific URLs and queries for real-time research updates.
- Native MCP Server: Full support for Model Context Protocol to facilitate seamless communication between different Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
ResearchVault
A high-velocity research orchestration engine that manages persistent state, synthesis, and autonomous verification for AI agents.
ResearchVault
An autonomous state management engine designed to orchestrate persistent research, synthesis, and verification for AI agents.
ResearchVault
A local-first orchestration engine that manages persistent research state, synthesis, and autonomous verification for AI agents.
ResearchVault
A local-first research orchestration engine designed to manage persistent state, synthesis, and autonomous verification for AI agents.
IMAP/SMTP Email Management Skill
A comprehensive email automation tool that enables AI agents to read, search, and send messages via standard IMAP and SMTP protocols.
tg-checkin Telegram Automation
A specialized Telegram Web automation skill that performs verified, serial check-ins across multiple groups based on your configuration.
Featured*
