searxng
Privacy-respecting metasearch using your local SearXNG instance. Search the web, images, news, and more without external API dependencies.
Why use this skill?
Enhance OpenClaw with private web search. Connect your SearXNG instance to perform privacy-respecting, multi-engine research without external tracking.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/phucanh08/searxng-1What This Skill Does
The SearXNG skill for OpenClaw provides a powerful, privacy-first interface to the internet by leveraging a local or self-hosted SearXNG instance. Unlike traditional search integrations that rely on third-party APIs which track user behavior or impose strict rate limits, this tool acts as a metasearch engine that aggregates results from over 70 different search engines into a single, clean interface. By running this locally, you maintain full control over your metadata and search history. The skill is highly modular, allowing you to search the general web, filter by specific media types like images or videos, and narrow results down by language or recency, making it an essential utility for researchers and power users alike.
Installation
To integrate this skill, use the Clawhub install command: clawhub install openclaw/skills/skills/phucanh08/searxng-1. After installation, ensure your environment is prepared by setting the SEARXNG_URL variable. If you are hosting your own instance, point this variable to your local URL (e.g., http://localhost:8080). You can define this in your shell profile or directly within the OpenClaw configuration file under the env section. If no URL is provided, the skill will default to http://localhost:8080, so ensure your service is running on that port.
Use Cases
This skill is perfect for scenarios requiring deep research without the "filter bubble" of centralized search engines. Use it to conduct private competitive analysis, gather raw data for natural language processing tasks, or find news updates across multiple international sources simultaneously. Its ability to output in JSON format makes it a robust component for automated agent workflows, where the agent can fetch data from the web and immediately process it into a structured format for further analysis or report generation.
Example Prompts
- "Search for the latest developments in generative AI technology and return the top 20 results."
- "Find images related to 'urban architecture in Tokyo' and provide the links."
- "Look up the latest news headlines about global renewable energy policy from today."
Tips & Limitations
To get the best results, always ensure your SearXNG instance is updated to the latest version, as the API structure can occasionally evolve. Because this tool relies on your own instance, it is only as fast and reliable as your network connection and the chosen back-end search engine engines enabled in your instance settings. If you receive empty results, check your SEARXNG_URL connectivity and verify that your instance has active engines configured. For automated pipelines, utilize the --format json flag to ensure the output remains machine-readable, avoiding the overhead of parsing raw text.
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-phucanh08-searxng-1": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api
Related Skills
codex-cli
Use OpenAI Codex CLI for coding tasks. Triggers: codex, code review, fix CI, refactor code, implement feature, coding agent, gpt-5-codex. Enables Clawdbot to delegate coding work to Codex CLI as a subagent or direct tool.
web-search
Search the web for real-time information.
multi-search-engine
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.
google-search
Google web search via Gemini Search Grounding (primary) and Custom Search JSON API (fallback). Use for: (1) Synthesized answers with citations (grounded search), (2) Raw link results with snippets, (3) Image search. Excellent Hebrew support. Preferred over built-in web_search (Perplexity).
Weather Api 1
Fetch weather data for construction scheduling. Historical data, forecasts, and risk assessment for outdoor work.