Vault for Openclaw

A local orchestration engine for managing long-running research tasks with high reliability and zero external costs.

lraivisto
v2.0.4
Feb 6, 2026
0
0
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install researchvault-brain

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install researchvault-brain 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 Vault?

Vault is a robust local research orchestration and state management tool designed to enhance the capabilities of AI agents. By utilizing a local SQLite database, it allows users to manage complex, long-running research projects without incurring external costs or relying on cloud-based storage. As a specialized component within the Openclaw Skills ecosystem, Vault ensures that every research event is tracked with precision, including confidence scores and source attribution.

This skill is particularly valuable for developers who need a reliable way to start projects, log incremental progress, and eventually export their findings into structured formats. By keeping the orchestration engine local, it provides a high degree of privacy and performance, making it an essential utility for high-stakes research environments.

Vault Use Cases

  • Managing state for long-running research projects that require persistent tracking.
  • Consolidating multi-source research data while maintaining secure SSRF protection.
  • Generating automated project summaries and status reports for complex objectives.
  • Exporting organized research data into Markdown for documentation or reporting.

How Vault Works

  1. Initialize a Project: Create a unique research context by defining a project ID and a high-level objective.
  2. Multi-Source Ingestion: Use the unified scuttle command to gather data from various URLs, ensuring secure access through built-in SSRF protection.
  3. Continuous Monitoring: Track the research lifecycle by querying the local database for status updates and automated summaries.
  4. Result Exportation: Finalize the research by exporting the collected data into a structured Markdown file for external use.

Vault Setup

Vault is designed to work out of the box with minimal configuration. It utilizes a local SQLite database stored at ~/.researchvault/ by default.

# Initialize a new research project
python3 scripts/vault.py init --id "proj-v1" --objective "Define your research goal"

# (Optional) Customize the database location
export RESEARCHVAULT_DB="/path/to/your/custom/vault.db"

Vault Data Schema & Taxonomy

Vault organizes all research data within a local SQLite database, focusing on two primary entities: Projects and Instrumentation events. This structure is ideal for users integrating Openclaw Skills into their data-heavy workflows.

Feature Details
Storage Local SQLite database (~/.researchvault/)
Project Metadata ID, Objective, Start Time
Instrumentation Confidence Score (0.0-1.0), Source URL, Custom Tags
Persistence Local-only; database files are excluded from version control

Vault Advanced Features

  • SSRF protection for secure web-based research gathering.
  • Granular confidence scoring for every data point tracked within the vault.
  • Support for configurable database paths via environment variables to suit different Openclaw Skills environments.
  • Multi-format export capabilities allowing research to be moved into various documentation frameworks.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*