Quickstart Guide

Get Started in Minutes

This guide will walk you through creating your first autonomous agent and multi-agent swarm using Swarms. By the end of this tutorial, you’ll have a working agent and understand how to orchestrate multiple agents to work together.

Before you begin, make sure you’ve installed Swarms and configured your environment.

Your First Agent

An Agent is the fundamental building block of a swarm—an autonomous entity powered by an LLM + Tools + Memory.

Import the Agent class

Start by importing the Agent class from the swarms package:

from swarms import Agent

Initialize your agent

Create a new agent with basic configuration:

# Initialize a new agent
agent = Agent(
    model_name="gpt-5.4",  # Specify the LLM
    max_loops="auto",          # Set the number of interactions
    interactive=True,          # Enable interactive mode for real-time feedback
)

Key Parameters:

model_name: The language model to use (e.g., “gpt-5.4”, “claude-sonnet-4-6”)
max_loops: Number of reasoning iterations, or "auto" to let the agent plan, act, and decide when it is done (see Autonomous mode)
interactive: Prompt you for follow-up input after each response

Run your agent

Execute a task with your agent:

# Run the agent with a task
response = agent.run(
    "What are the key benefits of using a multi-agent system?"
)
print(response)

Complete code example

from swarms import Agent

# Initialize a new agent
agent = Agent(
    model_name="gpt-5.4",  # Specify the LLM
    max_loops="auto",          # Set the number of interactions
    interactive=True,          # Enable interactive mode for real-time feedback
)

# Run the agent with a task
response = agent.run(
    "What are the key benefits of using a multi-agent system?"
)
print(response)

Your First Swarm: Multi-Agent Collaboration

A Swarm consists of multiple agents working together. Let’s create a two-agent workflow for researching and writing a blog post.

Import required classes

Import both Agent and SequentialWorkflow:

from swarms import Agent, SequentialWorkflow

Create specialized agents

Define two agents with specific roles:

# Agent 1: The Researcher
researcher = Agent(
    agent_name="Researcher",
    system_prompt="Your job is to research the provided topic and provide a detailed summary.",
    model_name="gpt-5.4",
)

# Agent 2: The Writer
writer = Agent(
    agent_name="Writer",
    system_prompt="Your job is to take the research summary and write a beautiful, engaging blog post about it.",
    model_name="gpt-5.4",
)

The system_prompt defines each agent’s role and responsibilities. Be specific about what you want each agent to do.

Create a sequential workflow

Connect the agents in a pipeline where the researcher’s output feeds into the writer’s input:

# Create a sequential workflow where the researcher's output feeds into the writer's input
workflow = SequentialWorkflow(agents=[researcher, writer])

Run the workflow

Execute the workflow with a task:

# Run the workflow on a task
final_post = workflow.run(
    "The history and future of artificial intelligence"
)
print(final_post)

The workflow will:

Send the task to the Researcher agent
The Researcher analyzes the topic and provides a summary
The Writer receives the research and creates a blog post
The final blog post is returned

Complete swarm example

from swarms import Agent, SequentialWorkflow

# Agent 1: The Researcher
researcher = Agent(
    agent_name="Researcher",
    system_prompt="Your job is to research the provided topic and provide a detailed summary.",
    model_name="gpt-5.4",
)

# Agent 2: The Writer
writer = Agent(
    agent_name="Writer",
    system_prompt="Your job is to take the research summary and write a beautiful, engaging blog post about it.",
    model_name="gpt-5.4",
)

# Create a sequential workflow where the researcher's output feeds into the writer's input
workflow = SequentialWorkflow(agents=[researcher, writer])

# Run the workflow on a task
final_post = workflow.run(
    "The history and future of artificial intelligence"
)
print(final_post)

Understanding the Workflow

The SequentialWorkflow executes agents in order, creating a pipeline where each agent builds upon the work of the previous one. This is ideal for:

Research → Analysis → Writing workflows
Data Collection → Processing → Reporting pipelines
Planning → Execution → Review processes
Any task with clear sequential dependencies

Want to run agents in parallel instead? Check out ConcurrentWorkflow for simultaneous execution.

What You Can Do Next

Add Tools to Your Agent

Extend your agent’s capabilities with external tools and APIs

Explore Multi-Agent Architectures

Learn about HierarchicalSwarm, ConcurrentWorkflow, MixtureOfAgents, and more

Use Different Model Providers

Connect to OpenAI, Anthropic, Groq, Cohere, and other LLM providers

Build Production Applications

Handle errors, control costs, and scale agents in production

Common Use Cases

Single Agent Examples

# Customer Support Agent
customer_support = Agent(
    agent_name="Customer-Support",
    system_prompt="You are a helpful customer support agent. Respond professionally and empathetically to customer inquiries.",
    model_name="gpt-5.4",
    max_loops=1,
)

response = customer_support.run(
    "I haven't received my order yet. What should I do?"
)

Multi-Agent Examples

# Financial Analysis Swarm
from swarms import Agent, ConcurrentWorkflow

market_analyst = Agent(
    agent_name="Market-Analyst",
    system_prompt="Analyze market trends and provide insights.",
    model_name="gpt-5.4",
)

financial_analyst = Agent(
    agent_name="Financial-Analyst",
    system_prompt="Provide financial analysis and recommendations.",
    model_name="gpt-5.4",
)

risk_analyst = Agent(
    agent_name="Risk-Analyst",
    system_prompt="Assess risks and provide risk management strategies.",
    model_name="gpt-5.4",
)

# Run all analysts concurrently
concurrent_workflow = ConcurrentWorkflow(
    agents=[market_analyst, financial_analyst, risk_analyst]
)

results = concurrent_workflow.run(
    "Analyze the potential impact of AI technology on the healthcare industry"
)

Troubleshooting

Agent not responding

Make sure your API keys are properly configured in your .env file. Check the environment setup guide for details.

Model not found error

Verify that you’re using a valid model name. See the Model Providers documentation for supported models.

Rate limit errors

Use max_loops=1 to reduce API calls. Each agent already retries a failed LLM call retry_attempts times (default 3); after that, run() tries any fallback_models you configured and then raises AgentLLMError. Catch it to add your own backoff.

Next Steps

Now that you’ve created your first agent and swarm, you’re ready to:

Customize your agents with specific system prompts and configurations
Add tools to extend agent capabilities
Explore different workflows like HierarchicalSwarm and MixtureOfAgents
Build production applications with advanced features

Join our Discord community to get help, share your projects, and connect with other Swarms developers!

Getting Started

Core Concepts

Agent Development

Reasoning Agents

Multi-Agent Architectures

Deployment & Operations

Integrations

CLI Reference

Changelog

Quickstart Guide

Get Started in Minutes

Your First Agent

Your First Swarm: Multi-Agent Collaboration

Understanding the Workflow

What You Can Do Next

Add Tools to Your Agent

Explore Multi-Agent Architectures

Use Different Model Providers

Build Production Applications

Common Use Cases

Single Agent Examples

Multi-Agent Examples

Troubleshooting

Next Steps

​Get Started in Minutes

​Your First Agent

​Your First Swarm: Multi-Agent Collaboration

​Understanding the Workflow

​What You Can Do Next

Add Tools to Your Agent

Explore Multi-Agent Architectures

Use Different Model Providers

Build Production Applications

​Common Use Cases

​Single Agent Examples

​Multi-Agent Examples

​Troubleshooting

​Next Steps

Get Started in Minutes

Your First Agent

Your First Swarm: Multi-Agent Collaboration

Understanding the Workflow

What You Can Do Next

Common Use Cases

Single Agent Examples

Multi-Agent Examples

Troubleshooting

Next Steps