agent-squad

<h2 align="center">Agent Squad</h2>
<p align="center">Flexible, lightweight open-source framework for orchestrating multiple AI agents to handle complex conversations.</p>

---
<p align="center">
  <strong>📦 New Home:</strong> Agent Squad has moved! Previously hosted at <strong>awslabs/agent-squad</strong>, this project is now maintained at <strong>2fastlabs/agent-squad</strong>.<br>
  Please update your bookmarks, clone URLs, and dependencies accordingly.
</p>

---


<p align="center">
  <a href="https://github.com/2fastlabs/agent-squad"><img alt="GitHub Repo" src="https://img.shields.io/badge/GitHub-Repo-green.svg" /></a>
  <a href="https://www.npmjs.com/package/agent-squad"><img alt="npm" src="https://img.shields.io/npm/v/agent-squad.svg?style=flat-square"></a>
  <a href="https://pypi.org/project/agent-squad/"><img alt="PyPI" src="https://img.shields.io/pypi/v/agent-squad.svg?style=flat-square"></a>
</p>

<p align="center">
  <!-- GitHub Stats -->
  <img src="https://img.shields.io/github/stars/awslabs/agent-squad?style=social" alt="GitHub stars">
  <img src="https://img.shields.io/github/forks/awslabs/agent-squad?style=social" alt="GitHub forks">
  <img src="https://img.shields.io/github/watchers/awslabs/agent-squad?style=social" alt="GitHub watchers">
</p>

<p align="center">
  <!-- Repository Info -->
  <img src="https://img.shields.io/github/last-commit/awslabs/agent-squad" alt="Last Commit">
  <img src="https://img.shields.io/github/issues/awslabs/agent-squad" alt="Issues">
  <img src="https://img.shields.io/github/issues-pr/awslabs/agent-squad" alt="Pull Requests">
</p>

<p align="center">
  <a href="https://2fastlabs.github.io/agent-squad/" style="display: inline-block; background-color: #0066cc; color: white; padding: 10px 20px; text-decoration: none; border-radius: 5px; font-weight: bold; font-size: 15px; transition: background-color 0.3s;">
    📚 Explore Full Documentation
  </a>
</p>


## 🔖 Features

- 🧠 **Intelligent intent classification** — Dynamically route queries to the most suitable agent based on context and content.
- 🔤 **Dual language support** — Fully implemented in both **Python** and **TypeScript**.
- 🌊 **Flexible agent responses** — Support for both streaming and non-streaming responses from different agents.
- 📚 **Context management** — Maintain and utilize conversation context across multiple agents for coherent interactions.
- 🔧 **Extensible architecture** — Easily integrate new agents or customize existing ones to fit your specific needs.
- 🌐 **Universal deployment** — Run anywhere - from AWS Lambda to your local environment or any cloud platform.
- 📦 **Pre-built agents and classifiers** — A variety of ready-to-use agents and multiple classifier implementations available.


## What Is Agent Squad ❓

The Agent Squad is a flexible framework for managing multiple AI agents and handling complex conversations. It intelligently routes queries and maintains context across interactions.

The system offers pre-built components for quick deployment, while also allowing easy integration of custom agents and conversation messages storage solutions.

This adaptability makes it suitable for a wide range of applications, from simple chatbots to sophisticated AI systems, accommodating diverse requirements and scaling efficiently.

<hr/>

## 🏗️ High-level architecture flow diagram

<br /><br />

![High-level architecture flow diagram](https://raw.githubusercontent.com/2fastlabs/agent-squad/main/img/flow.jpg)

<br /><br />

1. The process begins with user input, which is analyzed by a Classifier.
2. The Classifier leverages both Agents' Characteristics and Agents' Conversation history to select the most appropriate agent for the task.
3. Once an agent is selected, it processes the user input.
4. The orchestrator then saves the conversation, updating the Agents' Conversation history, before delivering the response back to the user.


## ![](https://raw.githubusercontent.com/2fastlabs/agent-squad/main/img/new.png) Introducing SupervisorAgent: Agents Coordination

The Agent Squad now includes a powerful new SupervisorAgent that enables sophisticated team coordination between multiple specialized agents. This new component implements a "agent-as-tools" architecture, allowing a lead agent to coordinate a team of specialized agents in parallel, maintaining context and delivering coherent responses.

![SupervisorAgent flow diagram](https://raw.githubusercontent.com/2fastlabs/agent-squad/main/img/flow-supervisor.jpg)

Key capabilities:
- 🤝 **Team Coordination** - Coordinate multiple specialized agents working together on complex tasks
- ⚡ **Parallel Processing** - Execute multiple agent queries simultaneously
- 🧠 **Smart Context Management** - Maintain conversation history across all team members
- 🔄 **Dynamic Delegation** - Intelligently distribute subtasks to appropriate team members
- 🤖 **Agent Compatibility** - Works with all agent types (Bedrock, Anthropic, Lex, etc.)

The SupervisorAgent can be used in two powerful ways:
1. **Direct Usage** - Call it directly when you need dedicated team coordination for specific tasks
2. **Classifier Integration** - Add it as an agent within the classifier to build complex hierarchical systems with multiple specialized teams

Here are just a few examples where this agent can be used:
- Customer Support Teams with specialized sub-teams
- AI Movie Production Studios
- Travel Planning Services
- Product Development Teams
- Healthcare Coordination Systems


[Learn more about SupervisorAgent →](https://2fastlabs.github.io/agent-squad/agents/built-in/supervisor-agent)


## 💬 Demo App

In the screen recording below, we demonstrate an extended version of the demo app that uses 6 specialized agents:
- **Travel Agent**: Powered by an Amazon Lex Bot
- **Weather Agent**: Utilizes a Bedrock LLM Agent with a tool to query the open-meteo API
- **Restaurant Agent**: Implemented as an Amazon Bedrock Agent
- **Math Agent**: Utilizes a Bedrock LLM Agent with two tools for executing mathematical operations
- **Tech Agent**: A Bedrock LLM Agent designed to answer questions on technical topics
- **Health Agent**: A Bedrock LLM Agent focused on addressing health-related queries

Watch as the system seamlessly switches context between diverse topics, from booking flights to checking weather, solving math problems, and providing health information.
Notice how the appropriate agent is selected for each query, maintaining coherence even with brief follow-up inputs.

The demo highlights the system's ability to handle complex, multi-turn conversations while preserving context and leveraging specialized agents across various domains.

![](https://raw.githubusercontent.com/2fastlabs/agent-squad/main/img/demo-app.gif?raw=true)


## 🎯 Examples & Quick Start

Get hands-on experience with the Agent Squad through our diverse set of examples:

- **Demo Applications**:
  - [Streamlit Global Demo](https://github.com/2fastlabs/agent-squad/tree/main/examples/python): A single Streamlit application showcasing multiple demos, including:
    - AI Movie Production Studio
    - AI Travel Planner
  - [Chat Demo App](https://2fastlabs.github.io/agent-squad/cookbook/examples/chat-demo-app/):
    - Explore multiple specialized agents handling various domains like travel, weather, math, and health
  - [E-commerce Support Simulator](https://2fastlabs.github.io/agent-squad/cookbook/examples/ecommerce-support-simulator/): Experience AI-powered customer support with:
    - Automated response generation for common queries
    - Intelligent routing of complex issues to human support
    - Real-time chat and email-style communication
    - Human-in-the-loop interactions for complex cases
- **Sample Projects**: Explore our example implementations in the `examples` folder:
  - [`chat-demo-app`](https://github.com/2fastlabs/agent-squad/tree/main/examples/chat-demo-app): Web-based chat interface with multiple specialized agents
  - [`ecommerce-support-simulator`](https://github.com/2fastlabs/agent-squad/tree/main/examples/ecommerce-support-simulator): AI-powered customer support system
  - [`chat-chainlit-app`](https://github.com/2fastlabs/agent-squad/tree/main/examples/chat-chainlit-app): Chat application built with Chainlit
  - [`fast-api-streaming`](https://github.com/2fastlabs/agent-squad/tree/main/examples/fast-api-streaming): FastAPI implementation with streaming support
  - [`text-2-structured-output`](https://github.com/2fastlabs/agent-squad/tree/main/examples/text-2-structured-output): Natural Language to Structured Data
  - [`bedrock-inline-agents`](https://github.com/2fastlabs/agent-squad/tree/main/examples/bedrock-inline-agents): Bedrock Inline Agents sample
  - [`bedrock-prompt-routing`](https://github.com/2fastlabs/agent-squad/tree/main/examples/bedrock-prompt-routing): Bedrock Prompt Routing sample code


Examples are available in both Python and TypeScript. Check out our [documentation](https://2fastlabs.github.io/agent-squad/) for comprehensive guides on setting up and using the Agent Squad framework!

## 📚 Deep Dives: Stories, Blogs & Podcasts

Discover creative implementations and diverse applications of the Agent Squad:

- **[From 'Bonjour' to 'Boarding Pass': Multilingual AI Chatbot for Flight Reservations](https://community.aws/content/2lCi8jEKydhDm8eE8QFIQ5K23pF/from-bonjour-to-boarding-pass-multilingual-ai-chatbot-for-flight-reservations)**

  This article demonstrates how to build a multilingual chatbot using the Agent Squad framework. The article explains how to use an **Amazon Lex** bot as an agent, along with 2 other new agents to make it work in many languages with just a few lines of code.

- **[Beyond Auto-Replies: Building an AI-Powered E-commerce Support system](https://community.aws/content/2lq6cYYwTYGc7S3Zmz28xZoQNQj/beyond-auto-replies-building-an-ai-powered-e-commerce-support-system)**

  This article demonstrates how to build an AI-driven multi-agent system for automat