Back

Tavily web search for OpenClaw

A lightweight Tavily web search skill for OpenClaw that works without pip and without third-party Python packages.

Tech Stack :
Source Code
|
Live Demo
Tavily web search for OpenClaw

Tavily Web Search Skill for OpenClaw 🦀

A lightweight Tavily web search skill for OpenClaw that works without
and without third-party Python packages.
This skill is designed for minimal Linux environments such as:
  • Raspberry Pi
  • Ubuntu Server
  • small VPS setups
  • systems where installing Python packages is unavailable, restricted, or intentionally avoided
Instead of using the
SDK, this skill calls the Tavily REST API directly using Python's standard library.

Features

  • Tavily web search through direct REST API calls
  • No
    required
  • No external Python dependencies
  • Works well on Raspberry Pi and Ubuntu Server
  • Supports general search and news search
  • Supports answer summaries, images, and domain filtering
  • Easy to integrate into OpenClaw skills
  • Simple secret-file based API key setup

Why this version exists

The official Tavily Python SDK is convenient, but some environments do not have a practical or desirable
workflow.
This skill exists for setups where you want:
  • a small footprint
  • no package installation step
  • predictable deployment
  • compatibility with minimal server environments
  • a solution that keeps working even on systems where Python package installation is restricted
This is especially useful on Raspberry Pi, Ubuntu Server, and other minimal Linux systems where you may prefer to avoid virtual environments, extra package managers, or external Python dependencies for a simple search integration.

Folder Structure

Secret Setup

Create the secret directory:
Create the key file:
The file must contain only your raw Tavily API key:
Do not write:
Set permissions:

Usage

Basic search:
News-focused search:
Advanced search:
JSON output:

Supported Options

OptionDescription
required search query
or
or
number of results
disable answer summary
include parsed raw content
include image results
restrict to selected domains
filter out selected domains
output raw JSON

OpenClaw Integration

This skill is meant to be used from OpenClaw through
.
Typical usage flow:
  1. The user asks for web search or recent information
  2. OpenClaw invokes the Tavily skill
  3. The skill runs
  4. The script reads the API key from
  5. Results are returned in a format suitable for summarization

Why no pip is required

This project intentionally avoids the Tavily Python SDK and other third-party dependencies.
That means:
  • there is no
    step
  • there is no dependency on
  • there is no virtual environment requirement just to use the skill
  • deployment stays simple on minimal systems
The script uses only Python's standard library to call the Tavily REST API directly.

Security Notes

  • The
    directory should never be committed
  • Your API key should stay only on the target machine
  • This repository should contain code and documentation only
  • Add
    to
  • Keep
    readable only by the user or service that runs the skill
Example
entries:

Requirements

  • Python 3
  • Network access to Tavily API
  • A valid Tavily API key
  • No additional Python packages are required

Motivation

This project is especially useful for:
  • Raspberry Pi home server setups
  • Ubuntu Server deployments
  • minimal VPS environments
  • offline-managed or tightly controlled systems
  • users who want Tavily search without SDK installation
  • environments where
    is unavailable, restricted, or intentionally avoided

License

This project is licensed under the MIT License. See the LICENSE file for details.