Clawler for Openclaw

Clawler is a sophisticated web-search plugin for OpenClaw that enables AI agents to access real-time information through multiple specialized search providers.

maxpetretta
v2026.3.11-6
Mar 12, 2026
0
984
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install clawler

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install clawler 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 Clawler?

Clawler serves as an optional, high-performance web-search surface designed specifically for the OpenClaw ecosystem. It bridges the gap between AI reasoning and the live web by providing a unified interface to interact with various search engines and LLM-based search providers. By integrating this skill, developers can grant their agents the ability to fetch current documentation, news, and technical data with granular control over sources and result freshness.

As one of the most versatile Openclaw Skills, Clawler allows for a plug-and-play experience where users can switch between providers like Brave, Exa, or OpenAI depending on the specific requirements of the query. Whether you need raw links or synthesized answers with citations, Clawler organizes these capabilities into a single, cohesive toolset.

Clawler Use Cases

  • Retrieving the latest technical documentation or API references for software development.
  • Conducting market research or competitive analysis using real-time web data.
  • Verifying facts or gathering news updates that occurred after an LLM's knowledge cutoff.
  • Filtering search results to specific trusted domains using allow-lists for authoritative sourcing.
  • Synthesizing cited answers by leveraging answer-native providers like Perplexity or Tavily.

How Clawler Works

  1. The AI agent identifies a need for external information based on the user's prompt.
  2. The agent invokes the search_web tool, optionally specifying a preferred provider and filters.
  3. Clawler interfaces with the configured search provider (e.g., Brave, Tavily) using the provided API credentials.
  4. The plugin processes the raw search data, applying any domain inclusions or exclusions defined in the request.
  5. Structured search results or synthesized answers are returned to the agent to inform its next response.

Clawler Setup

To get started with this component of your Openclaw Skills, follow these steps:

# Initialize the Clawler setup flow
openclaw clawler setup

# Configure your preferred provider (e.g., set BRAVE_API_KEY or TAVILY_API_KEY)
# Verify the installation and provider status
openclaw clawler status

To make Clawler your primary search tool, you can optionally disable the built-in search by adding web_search to your tools.deny configuration file.

Clawler Data Schema & Taxonomy

Clawler utilizes a structured schema for its search_web tool to ensure precision. The following table outlines the primary parameters:

Parameter Type Description
query String The required search term or question.
provider String Optional override (e.g., exa, openai, brave, anthropic).
count Integer Maximum number of results to return.
freshness String Date filters like pd (past day), pw (week), or explicit ranges.
include_domains Array A list of specific domains to search within.
topic String Topical hints such as general, news, or finance.

Clawler Advanced Features

  • Multi-Provider Support: Seamlessly toggle between over 10 different search and AI backends within the Openclaw Skills framework.
  • Domain Filtering: Implementation of native or best-effort allow-lists and deny-lists for targeted research.
  • Installation-Wide Overrides: Ability to replace default system search tools by modifying tool permissions.
  • Freshness Control: Granular time-based filtering to ensure data relevancy.
  • Provider-Neutral Logic: Intelligent 'auto' selection that utilizes the first available configured provider for maximum reliability.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*