A privacy-respecting metasearch skill that aggregates results from Google, Bing, and DuckDuckGo via a self-hosted SearXNG instance.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install searxng-docker
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 searxng-docker 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 SearXNG Search Skill?
This skill enables AI agents to perform comprehensive web searches while maintaining complete privacy and data sovereignty. By leveraging a local SearXNG instance, the skill aggregates and deduplicates results from dozens of search engines—including Google, Bing, and DuckDuckGo—without requiring expensive API keys or exposing search queries to third-party trackers. It is an essential component for developers building resilient research tools within the Openclaw Skills ecosystem.
The skill provides granular control over search parameters, allowing agents to filter by category (like IT, science, or news), language, and time range. Because it is fully self-hosted via Docker, it ensures high availability and avoids the rate-limiting often associated with public search APIs, making it a robust choice for heavy-duty research tasks.
SearXNG Search Skill Use Cases
- Conducting broad web research across multiple engines simultaneously.
- Retrieving specialized results from IT, science, or news categories.
- Performing private searches without relying on third-party search engine APIs.
- Gathering time-sensitive information using specific date filters.
- Replacing unreliable or limited default web search tools.
How SearXNG Search Skill Works
- The AI agent triggers the search script with specific queries and optional filters.
- The Python script sends a request to the local SearXNG Docker container.
- SearXNG queries multiple configured engines (Google, Bing, etc.) in parallel.
- Results are aggregated, deduplicated, and ranked based on a confidence score.
- The skill returns a structured JSON response containing titles, URLs, and snippets back to the agent.
SearXNG Search Skill Setup
To deploy this skill as part of your Openclaw Skills library, use the provided Docker Compose configuration:
# 1. Generate a random secret key and update settings
sed -i "s/CHANGE_ME_TO_A_RANDOM_STRING/$(openssl rand -hex 16)/" docker/settings.yml
# 2. Launch the self-hosted SearXNG instance
docker compose -f docker/docker-compose.yml up -d
# 3. Verify the service is active
curl -s "http://127.0.0.1:8888/search?q=test&format=json"
Configuration can be customized by editing docker/settings.yml to enable or disable specific search engines.
SearXNG Search Skill Data Schema & Taxonomy
The skill returns structured data including metadata for each search result. The primary fields are outlined below:
| Field | Description |
|---|---|
title |
The title of the search result |
url |
The direct link to the content |
content |
A brief snippet or summary of the page |
engine |
The source engine (e.g., google, bing) |
score |
A numerical value representing result relevance |
category |
The specific search category (news, it, science, etc.) |
SearXNG Search Skill Advanced Features
- Multi-category support including it, science, news, and social media.
- Language-specific searching using the -l flag (e.g., zh for Chinese, en for English).
- Time-range filtering (day, week, month) for up-to-date research.
- Cross-engine result deduplication and ranking scores.
- Custom base-URL support for remote SearXNG instances.
SKILL.md
Loading
Related Openclaw Skills
Wordly Wisdom
A calibrated decision-making engine for AI agents based on Charlie Munger's mental models and disciplined judgment techniques.
Weekly Planner
A developer-friendly, file-based weekly planning system using TOML to manage tasks, time blocks, and calendar syncs.
track17
A comprehensive parcel tracking integration that connects AI agents to the 17TRACK API for real-time shipment monitoring and local data persistence.
Todoist API Skill
A comprehensive CLI and automation toolkit for managing Todoist tasks, projects, and workflows via the Todoist API v1.
Base Buds Mint
A specialized skill for AI agents to solve challenges and mint Base Buds NFTs on the Base mainnet using secure local signing.
Local Voice (FluidAudio TTS/STT)
A high-performance local voice processing engine for Apple Silicon that provides sub-second TTS and STT capabilities without cloud dependency.
Featured*
