searxng-localSearch the web using a self-hosted SearXNG instance. Privacy-respecting metasearch that aggregates results from multiple engines.
Install via ClawdBot CLI:
clawdbot install clockworksquirrel/searxng-localSearch the web using your self-hosted SearXNG instance. Privacy-respecting metasearch that aggregates results from Google, DuckDuckGo, Brave, Startpage, and 70+ other engines.
SearXNG running locally or on a server. Quick Docker setup:
mkdir -p ~/Projects/searxng/searxng
cd ~/Projects/searxng
# Create docker-compose.yml
cat > docker-compose.yml << 'EOF'
services:
searxng:
image: searxng/searxng:latest
container_name: searxng
ports:
- "8080:8080"
volumes:
- ./searxng:/etc/searxng:rw
environment:
- SEARXNG_BASE_URL=http://localhost:8080/
restart: unless-stopped
EOF
# Create settings.yml with JSON API enabled
cat > searxng/settings.yml << 'EOF'
use_default_settings: true
server:
secret_key: "change-me-to-random-string"
bind_address: "0.0.0.0"
port: 8080
search:
safe_search: 0
autocomplete: "google"
default_lang: "en"
formats:
- html
- json
EOF
# Start SearXNG
docker compose up -d
Set the SearXNG URL (defaults to http://localhost:8080):
export SEARXNG_URL="http://localhost:8080"
curl "http://localhost:8080/search?q=your+query&format=json" | jq '.results[:5]'
# General web search
curl "http://localhost:8080/search?q=query&categories=general&format=json"
# Images
curl "http://localhost:8080/search?q=query&categories=images&format=json"
# News
curl "http://localhost:8080/search?q=query&categories=news&format=json"
# Videos
curl "http://localhost:8080/search?q=query&categories=videos&format=json"
# IT/Tech documentation
curl "http://localhost:8080/search?q=query&categories=it&format=json"
# Science/Academic
curl "http://localhost:8080/search?q=query&categories=science&format=json"
curl "http://localhost:8080/search?q=query&language=en-US&format=json"
curl "http://localhost:8080/search?q=query&language=de-DE&format=json"
# Page 2 (results 11-20)
curl "http://localhost:8080/search?q=query&pageno=2&format=json"
Each result includes:
title - Result titleurl - Link to the result content - Snippet/descriptionengines - Array of search engines that returned this resultscore - Relevance score (higher = better)category - Result categoryAdd to your .zshrc or .bashrc:
searxng() {
local query="$*"
local url="${SEARXNG_URL:-http://localhost:8080}"
curl -s "${url}/search?q=$(echo "$query" | sed 's/ /+/g')&format=json" | \
jq -r '.results[:10][] | "[\(.score | floor)] \(.title)\n \(.url)\n \(.content // "No description")\n"'
}
Usage: searxng how to make sourdough bread
# Start
cd ~/Projects/searxng && docker compose up -d
# Stop
docker compose down
# View logs
docker compose logs -f searxng
# Restart
docker compose restart
Container won't start:
docker compose logs searxng
JSON format not working:
Ensure formats: [html, json] is in your settings.yml
No results:
Some engines may be rate-limited. Check logs for errors.
Generated Feb 24, 2026
Researchers use the skill to aggregate search results from multiple academic and general sources without tracking, ensuring privacy while gathering diverse perspectives for literature reviews or data analysis. It supports categories like science and IT for targeted searches.
Business analysts leverage the skill to monitor competitors and industry trends across 70+ search engines anonymously, avoiding data collection by commercial platforms. It enables safe web scraping via JSON API for automated reports.
IT professionals set up a self-hosted instance to quickly search technical documentation and troubleshooting guides without relying on external APIs, using categories like IT for efficient problem-solving in secure environments.
Journalists use the skill to gather news and video content from diverse sources while maintaining privacy, with categories like news and videos for real-time updates without ads or tracking interference.
Educators and students deploy the skill in classrooms to provide ad-free, aggregated search results for projects, using language and region filters to tailor content while keeping data self-hosted for security.
Offer paid hosting, maintenance, and customization services for SearXNG instances, targeting businesses that need privacy-respecting search but lack technical expertise. Revenue comes from subscription fees for managed servers.
Develop and sell integrations that embed the SearXNG skill into enterprise tools for secure internal search, with revenue from licensing fees and support contracts for large organizations prioritizing data sovereignty.
Provide a hosted SearXNG service with enhanced features like analytics dashboards and premium support, monetizing through tiered pricing for individuals and small businesses seeking ad-free search alternatives.
💬 Integration Tip
Set the SEARXNG_URL environment variable to point to your instance, and use the JSON API format for easy parsing in automation scripts or applications.
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.
This skill should be used when users need to search the web for information, find current content, look up news articles, search for images, or find videos. It uses DuckDuckGo's search API to return results in clean, formatted output (text, markdown, or JSON). Use for research, fact-checking, finding recent information, or gathering web resources.
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
Search indexed Discord community discussions via Answer Overflow. Find solutions to coding problems, library issues, and community Q&A that only exist in Discord conversations.
Multi search engine integration with 17 engines (8 CN + 9 Global). Supports advanced search operators, time filters, site search, privacy engines, and WolframAlpha knowledge queries. No API keys required.