A versatile AI search tool that leverages the NanoGPT API to aggregate results from top providers like Tavily, Exa, and Perplexity.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install nano-web-search
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install nano-web-search 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 NanoGPT Web Search?
NanoGPT Web Search is a robust integration designed for developers who need reliable, AI-driven internet access. By tapping into the NanoGPT API, this Openclaw Skills entry provides a unified interface for multiple search engines, allowing for standard or deep research queries. Whether you need raw search results or a synthesized, sourced answer with citations, this skill streamlines the process of fetching real-time data for AI workflows. It acts as a bridge between your local environment and the world's leading search APIs, offering a single point of access for high-quality web data.
NanoGPT Web Search Use Cases
- Fetching real-time news or technical documentation for AI agents.
- Generating synthesized answers with citations using the sourcedAnswer output type.
- Performing deep research across specialized providers like Exa or Kagi.
- Automating data gathering for market research or competitive analysis.
- Integrating web search capabilities into Python-based automation scripts within the Openclaw Skills framework.
How NanoGPT Web Search Works
- The user provides a search query and optional parameters like provider or depth via CLI or Python.
- The skill authenticates with the NanoGPT API using a secured environment variable.
- The request is routed to the selected search provider, such as Tavily, Brave, or Perplexity.
- The skill processes the provider's response, formatting it as raw results, a structured object, or a synthesized answer.
- Results are returned to the user or agent in the requested format, such as CLI output, JSON, or a Python dictionary.
NanoGPT Web Search Setup
Install the necessary Python dependencies to begin using these Openclaw Skills:
pip install requests
Set the required environment variable for authentication:
export NANOGPT_API_KEY="sk-nano-your-key-here"
Ensure you have python3 and curl installed on your system to run the search scripts efficiently.
NanoGPT Web Search Data Schema & Taxonomy
The skill handles data through the following parameters and response structures:
| Component | Description |
|---|---|
| Provider | Choice of linkup, tavily, exa, kagi, perplexity, valyu, or brave. |
| Output Type | searchResults (raw list), sourcedAnswer (synthesized), or structured. |
| Filters | Supports date ranges (YYYY-MM-DD) and domain inclusion/exclusion. |
| Response | Returns a JSON object containing a 'data' array with title, url, and snippet fields. |
NanoGPT Web Search Advanced Features
- Deep search support for comprehensive data gathering beyond surface-level results.
- Multi-provider flexibility allowing users to switch search engines based on cost or accuracy needs.
- Native Python API support for seamless integration into larger software projects using Openclaw Skills.
- Granular domain filtering to white-list or black-list specific sources for improved data quality.
- Capability to output structured data directly for downstream consumption by other automated agents.
SKILL.md
Loading
Related Openclaw Skills
Bitwarden & Vaultwarden Integration
A powerful CLI wrapper for Bitwarden and Vaultwarden that enables AI agents to securely manage credentials with automatic session handling.
Sportsbet Advisor
A data-driven sports analysis tool that provides educated betting predictions and historical insights for informed wagering.
DualAgentSolver
A collaborative two-agent workflow that iteratively refines solutions through critique and merges the final output into persistent memory.
Dual Agent Debate
Run an automated, multi-round debate between ChatGPT and your stored personal knowledge to stress-test ideas and reach logical conclusions.
Revenue Calculator
A powerful projection tool for estimating monthly and annual revenue for AI agents and marketplace strategies.
Self-Improvement Skill
A structured logging and memory system that enables AI agents to capture errors, corrections, and best practices for continuous autonomous improvement.
Featured*
