Bocha Search for Openclaw

A high-precision web search skill for AI agents that delivers structured data and comprehensive summaries from across the web.

sunjingji
v1.0.0
Feb 10, 2026
0
3.5k
0

Install & Download

1. ClawHub CLI

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

npx clawhub@latest install bocha-search

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 bocha-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 Bocha Search?

Bocha Search is a powerful plugin designed to bridge the gap between AI agents and real-time web information. By leveraging the Bocha AI Search API, it allows Openclaw Skills to perform comprehensive web queries and receive structured results specifically formatted for large language models.

This skill ensures that your AI agents have access to the most accurate and up-to-date information across the entire internet. It is engineered to provide high-quality summaries and metadata, making it an essential tool for any developer building sophisticated agentic workflows that require grounding in real-world data.

Bocha Search Use Cases

  • Real-time fact-checking and news retrieval for AI-driven content creation.
  • Gathering structured data for market research and competitive analysis using Openclaw Skills.
  • Enhancing AI agent reasoning by providing detailed webpage summaries instead of just snippets.
  • Filtering search results by specific timeframes such as day, week, month, or year for temporal accuracy.

How Bocha Search Works

  1. The AI agent initiates a query through the Bocha Search CLI or integrated script.
  2. The skill processes the query and applies optional filters like result count, summary flags, or freshness constraints.
  3. A request is sent to the Bocha AI Search API using the configured API credentials.
  4. The API returns a structured JSON response containing webpage titles, URLs, descriptions, and optional deep summaries.
  5. The skill formats the output into a Bing-compatible structure for the AI agent to consume and process.

Bocha Search Setup

To get started, obtain your API key from the Bocha Open Platform.

Edit the config.json file within the skill directory:

{
  "apiKey": "sk-your-api-key"
}

Method 2: Environment Variable

Alternatively, set the key in your terminal session:

export BOCHA_API_KEY="sk-your-api-key"

Basic Usage

Run a search query directly from the command line:

node scripts/search.js "your search query" --summary

Bocha Search Data Schema & Taxonomy

The skill returns a standardized JSON object optimized for Openclaw Skills integration:

Field Type Description
type string The type of response (search or error).
totalResults number Total matches found globally.
results array Contains objects with title, url, description, and summary.
siteName string The name of the source website for the result.
publishedDate string ISO timestamp of the content publication.

Bocha Search Advanced Features

  • Temporal Filtering: Support for noLimit, oneDay, oneWeek, oneMonth, oneYear, and custom date ranges (YYYY-MM-DD..YYYY-MM-DD).
  • LLM-Ready Summaries: The --summary flag generates detailed content descriptions that improve the context window quality for AI agents.
  • Bing API Compatibility: Response formats are designed to be compatible with Bing Search API structures, easing the migration for existing Openclaw Skills.
  • Robust Error Handling: Includes specific error codes for parameter missing (400), invalid keys (401), insufficient balance (403), and rate limiting (429).

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*