Skip to content

Latest commit

 

History

History

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

readme.md

AWS Agent Squad Demos

This Streamlit application demonstrates the capabilities of the AWS Agent Squad framework by showcasing how specialized AI agents can collaborate to solve complex tasks using Amazon Bedrock and Anthropic's Claude models.

Demo app

🎯 Current Demos

Requirements: AWS Account with Amazon Bedrock access (Claude models enabled)

Bring your movie ideas to life with this AI-powered production assistant. Describe your movie concept, select a genre and target audience, and let the system create a comprehensive script outline and recommend actors for the main roles based on real-time research.

Requirements: Anthropic API Key

Enter your destination and travel duration, and the system will research attractions, accommodations, and activities in real-time to create a personalized, day-by-day itinerary based on your preferences.

🚀 Getting Started

Prerequisites

Installation

  1. Clone the repository:
git clone https://github.com/awslabs/agent-squad.git
cd agent-squad/examples/python
python -m venv venv
source venv/bin/activate # On Windows use `venv\Scripts\activate`
pip install -r requirements.txt
  1. Configure AWS credentials:

    • Follow the AWS documentation to set up your credentials using your preferred method (AWS CLI, environment variables, or credentials file)
  2. Run the Streamlit app:

streamlit run main-app.py

🎮 Featured Demos

🎬 AI Movie Production Studio

Prerequisite: AWS Account with Amazon Bedrock access (Claude models enabled)

Transform your movie ideas into detailed scripts and cast lists! Our AI agents collaborate:

  • ScriptWriter (BedrockLLMAgent with Claude 3 Sonnet): Creates compelling story outlines
  • CastingDirector (BedrockLLMAgent with Claude 3 Haiku): Researches and suggests perfect casting choices
  • MovieProducer (BedrockLLMAgent with Claude 3.5 Sonnet): Coordinates the entire creative process
  • All coordinated by a Custom Agent as Supervisor Agent

✈️ AI Travel Planner

Prerequisite: Anthropic API Key

Your personal travel assistant powered by AI! Experience collaboration between:

  • ResearcherAgent (AnthropicAgent with Claude 3 Haiku): Performs real-time destination research
  • PlannerAgent (AnthropicAgent with Claude 3 Sonnet): Creates personalized day-by-day itineraries
  • Coordinated by a Custom Agent as Supervisor Agent

🛠️ Technologies Used

  • Streamlit for UI
  • AWS Agent Squad for multi-agent collaboration
  • Amazon Bedrock for deploying Claude models
  • Anthropic's Claude models for AI reasoning
  • Python for backend scripting

📚 Documentation

Learn more about the AWS Agent Squad framework, including its features and technical details, by visiting the official documentation.

🤝 Contributing

If you want to create a new demo to be included in this global Streamlit demo application, contributions are welcome! Please fork the repository, create a new branch with your changes, and submit a Pull Request for review