Skip to main content
The BraveSearch tool lets an agent search the web through the Brave Search API.

​
Overview

The BraveSearch tool is a tool that allows you to search the web using the BraveSearch API. 
pip install langchain-community google-search-results

export BRAVE_SEARCH_API="${BRAVE_SEARCH_API:?Set BRAVE_SEARCH_API in your shell}"
export OPENAI_API_KEY="${OPENAI_API_KEY:?Set OPENAI_API_KEY in your shell}"

from praisonaiagents import Agent, AgentTeam
from langchain_community.tools import BraveSearch
import os


def search_brave(query: str):
    """Searches using BraveSearch and returns results."""
    api_key = os.environ['BRAVE_SEARCH_API']
    tool = BraveSearch.from_api_key(api_key=api_key, search_kwargs={"count": 3})
    return tool.run(query)

data_agent = Agent(instructions="Search about AI job trends in 2025", tools=[search_brave])
editor_agent = Agent(instructions="Write a blog article")
agents = AgentTeam(agents=[data_agent, editor_agent])
agents.start()
Generate your BraveSearch API key from BraveSearch

​
How It Works

​
Getting Started

1

Simple Usage

  1. Install dependencies (see Overview above)
  2. Set required API keys in your environment
  3. Run the agent example in Overview
2

With Configuration

Use the same tool with an agent — see the Overview example, or pass env vars from the sections above.

​
Best Practices

Read the key with os.environ['BRAVE_SEARCH_API'] and set it in your shell or a .env file. Never hard-code the key in the tool function.
BraveSearch.from_api_key accepts search_kwargs={"count": 3}. Keep count low so the agent processes fewer tokens and answers faster.
Brave returns HTTP 429 when the plan quota is exceeded. Wrap tool.run(query) in a try/except so the agent can fall back to another search tool instead of crashing.

DuckDuckGo

Privacy-focused search

Tavily

AI-powered search

Serper

Google search API