SearXNG Search for Openclaw

A privacy-respecting metasearch skill that aggregates results from over 70 engines into a single, self-hosted API for secure web research.

clockworksquirrel
v1.0.0
Jan 27, 2026
2
5.4k
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install searxng-local

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 searxng-local 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?

SearXNG is a robust metasearch engine that prioritizes user privacy by aggregating results from major search providers like Google, Bing, and Brave without tracking user behavior. This skill enables AI agents to perform comprehensive web research using a self-hosted instance, ensuring that search queries and data remain entirely under the user's control. By leveraging Openclaw Skills, developers can integrate high-quality, unbiased search results directly into their automated workflows or agentic scripts without relying on expensive or privacy-invasive third-party APIs.

SearXNG Search Use Cases

  • Performing private web research without being tracked by commercial search engines.
  • Aggregating technical documentation and IT-specific results from multiple sources simultaneously.
  • Automating news gathering or academic paper searches for AI-driven summaries.
  • Building secure agents that require internet access without exposing sensitive queries to third-party trackers.
  • Fetching region-specific or language-specific search data for localized AI tasks.

How SearXNG Search Works

  1. The skill connects to a self-hosted SearXNG instance via a specified URL endpoint defined in the environment variables.
  2. A query is sent to the instance with specific formatting and optional category filters such as IT, Science, or News.
  3. SearXNG queries over 70 upstream engines simultaneously and aggregates the findings while stripping tracking data.
  4. Results are processed into a structured JSON format including relevance scores, source engines, and content snippets.
  5. The AI agent parses the top-ranked results to extract the necessary information to complete the user's task within the Openclaw Skills framework.

SearXNG Search Setup

First, set up a local Docker instance of SearXNG. Create a docker-compose.yml and a settings.yml ensuring that the JSON format is enabled in the configuration. Start the service using:

docker compose up -d

Then, configure the skill by setting the environment variable to point to your local instance:

export SEARXNG_URL="http://localhost:8080"

Ensure your settings.yml allows JSON output to enable seamless integration with Openclaw Skills.

SearXNG Search Data Schema & Taxonomy

The skill returns a collection of result objects with the following metadata taxonomy:

Field Description
title The display title of the search result
url The direct link to the source content
content A brief snippet or description of the result page
engines An array of search engines that returned this specific result
score A calculated relevance score used for ranking results
category The content category such as general, images, or news

SearXNG Search Advanced Features

  • Multi-category searching including specialized IT and Science silos for deeper technical research.
  • Support for paginated result fetching to handle extensive data gathering tasks beyond the first page.
  • Language and regional filtering to customize results for specific locales and international requirements.
  • Shell function integration for quick CLI-based search access within Openclaw Skills development environments.
  • High-performance aggregation from over 70 search engines with no API keys or rate limits required.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*