ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 4/5

searxng

Search the web using a self-hosted SearXNG instance. Privacy-respecting metasearch that aggregates results from multiple engines.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/clockworksquirrel/searxng-metasearch
Or

What This Skill Does

The SearXNG search skill enables OpenClaw to perform web searches using a privacy-respecting metasearch engine. Instead of relying on a single data source, this skill queries multiple engines simultaneously—including Google, DuckDuckGo, Brave, and Startpage—and aggregates the results into a unified JSON format. It is designed to be hosted locally, ensuring that your search queries remain private and are not tracked by centralized advertising entities. By leveraging SearXNG, OpenClaw gains the ability to fetch up-to-date information, technical documentation, news, and academic research directly from the web, providing a more robust and contextual knowledge base for its reasoning tasks.

Installation

To use this skill, you must first have a running instance of SearXNG. You can deploy this easily via Docker by creating a directory for the configuration, setting up a docker-compose.yml file, and defining the settings.yml to enable the JSON API format. Once your container is running on your local machine or server, use the OpenClaw CLI to install the skill by running: clawhub install openclaw/skills/skills/clockworksquirrel/searxng-metasearch. Finally, export the environment variable SEARXNG_URL to point to your instance (e.g., export SEARXNG_URL="http://localhost:8080"), ensuring OpenClaw can communicate with your local search backend.

Use Cases

This skill is ideal for research-intensive workflows. Use it to verify facts, fetch technical documentation for specific programming libraries, or gather diverse perspectives on current events by analyzing results from multiple search engines simultaneously. It is particularly useful for developers who need to quickly find solutions on StackOverflow, GitHub, or official documentation sites without relying on proprietary, opaque search algorithms. Additionally, the ability to categorize searches—such as filtering specifically for images, videos, or academic papers—makes it a versatile tool for media curation and scholarly data collection.

Example Prompts

  1. "Search for the latest documentation on Rust ownership and borrowing and summarize the key concepts."
  2. "Look up the most recent news regarding open-source AI frameworks released in the last month."
  3. "Find technical guides on setting up a Kubernetes cluster using the latest best practices."

Tips & Limitations

To maximize the utility of this skill, ensure your settings.yml is configured for high-quality results by keeping safe search settings appropriate for your use case. Be aware that because this is a metasearch engine, response times depend on the speed of the slowest underlying search engine provider. Avoid excessive rapid-fire requests to prevent being rate-limited by upstream engines. Always verify the content snippet against the provided url for complete context, as search snippets are truncated by design.

Metadata

Stars3453
Views7
Updated2026-03-26
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-clockworksquirrel-searxng-metasearch": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#search#privacy#metasearch#web-scraping#docker
Safety Score: 4/5

Flags: network-access