Deep Private Search for Openclaw

A secure, VPN-mandated search skill using local SearXNG for multi-iteration private research without tracking or rate limits.

romancircus
v1.0.8
Feb 4, 2026
0
0
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install privatedeepsearch-claw

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 privatedeepsearch-claw 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 Deep Private Search?

Deep Private Search is a privacy-first research tool designed to prevent Big Tech from monitoring your activities or building a behavioral profile. By leveraging a local SearXNG instance and mandatory VPN routing, this skill ensures your search patterns, location, and real IP address remain completely hidden. It is a core component of the Openclaw Skills ecosystem, providing developers and researchers with a way to gather data across 40+ engines without the restrictions of traditional search APIs.

This tool prioritizes anonymity while maintaining performance levels comparable to mainstream search engines, offering high-speed results without the privacy trade-offs. It allows your AI agent to perform deep, recursive dives into complex topics while maintaining a zero-footprint digital presence.

Deep Private Search Use Cases

  • Performing deep, multi-iteration research without exposing search history to corporate search providers.
  • Scraping full website content for AI analysis while remaining completely anonymous through VPN routing.
  • Evading rate limits and IP-based blocking during intensive data gathering tasks using local SearXNG.
  • Conducting sensitive competitor analysis or market research without leaving geographic or behavioral trails.

How Deep Private Search Works

  1. The skill initiates a local SearXNG instance to process queries internally, ensuring no external calls are made to tracking APIs.
  2. All outgoing search traffic is automatically routed through a host-level VPN to mask the user's real IP address from search engines.
  3. The agent performs parallel processing across 40+ privacy-focused engines, including DuckDuckGo, Brave, and Startpage.
  4. It executes a 5-iteration recursive search process to refine results and drill down into complex technical topics.
  5. The system scrapes full content from discovered pages rather than relying on snippets, feeding high-quality data back to the agent.

Deep Private Search Setup

To effectively use this addition to your Openclaw Skills library, a VPN must be active on your host machine.

Option 1: ProtonVPN Setup

wget https://repo.protonvpn.com/debian/dists/all/main/binary-amd64/protonvpn-stable-release_1.0.3_all.deb
sudo dpkg -i protonvpn-stable-release_1.0.3_all.deb
sudo apt update && sudo apt install protonvpn
protonvpn login
protonvpn connect --fastest

Option 2: Mullvad Setup

curl -L https://mullvad.net/download/app/linux/latest --output mullvad.deb
sudo dpkg -i mullvad.deb
mullvad account set [YOUR_ACCOUNT_NUMBER]
mullvad connect

Verification

curl -s ifconfig.me

Verify that the output shows your VPN server IP and not your local ISP address.

Deep Private Search Data Schema & Taxonomy

The skill organizes its research findings into a structured format for the AI agent to parse and analyze.

Field Description
Query The refined search string used for a specific iteration.
Source Engine The specific privacy engine that provided the result.
Full Content The complete scraped text from the destination URL.
Iteration Depth The level of recursive refinement (1-5) for the current search.
Privacy Status Confirmation of VPN routing and IP masking for the request.

Deep Private Search Advanced Features

  • Multi-iteration recursive search that automatically refines queries based on previous findings.
  • Native support for Mullvad, Tailscale, and ProtonVPN host-level routing.
  • Parallel processing capabilities to query over 40 privacy-focused engines simultaneously.
  • Full content scraping that bypasses standard search snippets for comprehensive data ingestion.
  • Zero-tracking architecture that ensures no search history or profile building is possible.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*