857★by romancircus
searxng – OpenClaw Skill
searxng is an OpenClaw Skills integration for coding workflows. Privacy-first web search via local SearXNG instance. Google-free meta-search using DuckDuckGo, Brave, Qwant, Startpage, and more. Use for any web search query.
Skill Snapshot
| name | searxng |
| description | Privacy-first web search via local SearXNG instance. Google-free meta-search using DuckDuckGo, Brave, Qwant, Startpage, and more. Use for any web search query. OpenClaw Skills integration. |
| owner | romancircus |
| repository | romancircus/privatedeepsearch-clawpath: skills/searxng |
| language | Markdown |
| license | MIT |
| topics | |
| security | L1 |
| install | openclaw add @romancircus/privatedeepsearch-claw:skills/searxng |
| last updated | Feb 7, 2026 |
Maintainer

name: searxng description: Privacy-first web search via local SearXNG instance. Google-free meta-search using DuckDuckGo, Brave, Qwant, Startpage, and more. Use for any web search query. homepage: http://localhost:8888 metadata: {"clawdbot":{"emoji":"🔍","requires":{"bins":["curl","jq"]}}}
SearXNG - Private Web Search
Local SearXNG instance at http://localhost:8888 with Google/Bing disabled.
Search (JSON API)
Basic search:
curl -s "http://localhost:8888/search?q=YOUR_QUERY&format=json" | jq -r '.results[:5] | .[] | "[\(.title)](\(.url))\n\(.content)\n"'
With result limit:
curl -s "http://localhost:8888/search?q=YOUR_QUERY&format=json" | jq -r '.results[:10] | .[] | {title, url, content}'
Get just URLs:
curl -s "http://localhost:8888/search?q=YOUR_QUERY&format=json" | jq -r '.results[:5] | .[].url'
Categories
Search specific categories:
# Images
curl -s "http://localhost:8888/search?q=YOUR_QUERY&categories=images&format=json" | jq '.results[:5]'
# Videos
curl -s "http://localhost:8888/search?q=YOUR_QUERY&categories=videos&format=json" | jq '.results[:5]'
# News
curl -s "http://localhost:8888/search?q=YOUR_QUERY&categories=news&format=json" | jq '.results[:5]'
# IT/Tech
curl -s "http://localhost:8888/search?q=YOUR_QUERY&categories=it&format=json" | jq '.results[:5]'
# Science
curl -s "http://localhost:8888/search?q=YOUR_QUERY&categories=science&format=json" | jq '.results[:5]'
Time Filters
Recent results:
# Last day
curl -s "http://localhost:8888/search?q=YOUR_QUERY&time_range=day&format=json" | jq '.results[:5]'
# Last week
curl -s "http://localhost:8888/search?q=YOUR_QUERY&time_range=week&format=json" | jq '.results[:5]'
# Last month
curl -s "http://localhost:8888/search?q=YOUR_QUERY&time_range=month&format=json" | jq '.results[:5]'
# Last year
curl -s "http://localhost:8888/search?q=YOUR_QUERY&time_range=year&format=json" | jq '.results[:5]'
Language/Region
# English results
curl -s "http://localhost:8888/search?q=YOUR_QUERY&language=en&format=json" | jq '.results[:5]'
# Specific region (US)
curl -s "http://localhost:8888/search?q=YOUR_QUERY&language=en-US&format=json" | jq '.results[:5]'
Enabled Search Engines
Privacy-respecting only (no Google, Bing):
- DuckDuckGo (weight 1.5)
- Brave Search (weight 1.5)
- Startpage (weight 1.2)
- Mojeek (weight 1.0)
- Qwant (weight 1.0)
- Wikipedia (weight 1.5)
- GitHub
- StackOverflow
- arXiv
- Piped/Invidious (YouTube privacy frontends)
Tips
- URL-encode spaces:
q=hello%20worldorq=hello+world - Combine filters:
categories=news&time_range=week - For complex queries, use the web UI: http://localhost:8888
Example Usage
Find recent AI news:
curl -s "http://localhost:8888/search?q=artificial+intelligence+news&categories=news&time_range=week&format=json" | jq -r '.results[:5] | .[] | "## \(.title)\n\(.url)\n\(.content)\n"'
Search GitHub repos:
curl -s "http://localhost:8888/search?q=python+web+scraper&categories=repos&format=json" | jq '.results[:5]'
No README available.
Permissions & Security
Security level L1: Low-risk skills with minimal permissions. Review inputs and outputs before running in production.
Requirements
- OpenClaw CLI installed and configured.
- Language: Markdown
- License: MIT
- Topics:
FAQ
How do I install searxng?
Run openclaw add @romancircus/privatedeepsearch-claw:skills/searxng in your terminal. This installs searxng into your OpenClaw Skills catalog.
Does this skill run locally or in the cloud?
OpenClaw Skills execute locally by default. Review the SKILL.md and permissions before running any skill.
Where can I verify the source code?
The source repository is available at https://github.com/openclaw/skills/tree/main/skills/romancircus/privatedeepsearch-claw. Review commits and README documentation before installing.
