Skip to content

strands-agents/samples

Strands Agents Samples

A model-driven approach to building AI agents in just a few lines of code.

GitHub commit activity GitHub open issues GitHub open pull requests License

DocumentationSamplesPython SDKTypeScript SDK NewToolsAgent BuilderMCP Server

Welcome to the Strands Agents Samples repository!

Explore easy-to-use examples to get started with Strands Agents.

The examples in this repository are for demonstration and educational purposes only. They demonstrate concepts and techniques but are not intended for direct use in production. Always apply proper security and testing procedures before using in production environments.

Quick Start

Python Python

Prerequisites:

  • Python 3.10 or higher
  • pip package manager
    • Verify with: pip --version or pip3 --version
    • Usually comes bundled with Python 3.4+ installers from python.org
    • If pip is missing, install using one of these methods:
      # Method 1 - Use Python's built-in module
      python -m ensurepip --upgrade
      
      # Method 2 - Download and run the official installer
      curl https://bootstrap.pypa.io/get-pip.py -o get-pip.py
      python get-pip.py

Step 1: Create Virtual Environment

# Create virtual environment
python -m venv venv

# Activate virtual environment
# On macOS/Linux:
source venv/bin/activate
# On Windows:
venv\Scripts\activate

Step 2: Install

pip install strands-agents strands-agents-tools

Your First Agent:

from strands import Agent

agent = Agent()
response = agent("Hello! Tell me a joke.")
print(response)

Explore Python tutorials →

TypeScript TypeScript

Prerequisites:

  • Node.js 18 or higher
  • npm or yarn package manager

Install:

npm install @strands-agents/sdk

Your First Agent:

import { Agent } from "@strands-agents/sdk";

async function main() {
    const agent = new Agent({
        systemPrompt: "You are a helpful assistant."
    });

    const response = await agent.invoke("Hello! Tell me a joke.");
    console.log(response.toString());
}

main();

Explore TypeScript tutorials →

Model Provider Setup

Follow the instructions here to configure your model provider and model access.

Explore the Repository

Python Samples

  • 01-learn - SDK tutorials covering fundamentals, multi-agent systems, and streaming
  • 02-deploy - Deployment patterns for Lambda, Fargate, and AgentCore
  • 03-integrate - Integrations with AWS services, databases, and third-party tools
  • 04-industry-use-cases - Industry applications (finance, healthcare, retail, productivity, etc.)
  • 05-technical-use-cases - Architectural patterns including Agentic RAG
  • 06-evaluate - Evaluation tutorials and testing patterns
  • 07-ux-demos - Full-stack applications with user interfaces
  • 08-edge - Edge device integrations including physical AI and robotics

TypeScript Samples

  • 01-learn - SDK tutorials for the TypeScript SDK
  • 02-deploy - Deployment patterns for AgentCore

Contributing ❤️

We welcome contributions! See our Contributing Guide for details on:

  • Reporting bugs & features
  • Development setup
  • Contributing via Pull Requests
  • Code of Conduct
  • Reporting of security issues

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

Security

See CONTRIBUTING for more information.