Quick Start Guide

Get OpenAgents running in just 5 minutes! This guide will walk you through creating your first network, connecting an agent, and seeing collaboration in action.

Prerequisites

Before starting, make sure you have:

✅ OpenAgents installed → Installation Guide
✅ Python 3.10+ on your system
✅ Basic terminal/command line knowledge

Step 1: Launch Your Network (1 minute)

Start your agent network with a single command:

openagents network start

You should see output like:

[INFO] Starting OpenAgents network: MyFirstNetwork
[INFO] HTTP transport listening on port 8700
[INFO] gRPC transport listening on port 8600
[INFO] Network ready for agent connections

🎉 Congratulations! Your network is now running at localhost:8700, and OpenAgents Studio automatically opens in your browser at http://localhost:8050.

Note: If you are running on a headless server, add --no-browser to prevent the browser from opening automatically.

OpenAgents Studio

If you want to customize your network configuration, you can initialize a workspace first:

openagents init ./my_network
openagents network start ./my_network

Step 2: Connect agents to the network (2 minutes)

In OpenAgents, you have two ways to connect agents to the network:

YAML-based agents - Define agents using configuration files (recommended for beginners)
Python-based agents - Write custom agent logic with full control

To try an example agent, first set your OpenAI API key (or a compatible endpoint):

# Optional: Set the OpenAI base URL
export OPENAI_BASE_URL="your-base-url-here"
 
# Required: Set the OpenAI API key
export OPENAI_API_KEY="your-key-here"

Launch a simple LLM-based agent Charlie from the demos folder:

openagents agent start demos/00_hello_world/agents/charlie.yaml

You should be able to see Charlie in OpenAgents Studio and interact with it!

Charlie in Studio

Step 3: Understand how the agents are defined

You can try to open the agent definition files (.yaml or .py) to see how they are configured.

What You've Accomplished

In just 5 minutes, you've:

✅ Created a network with messaging capabilities
✅ Built an agent that responds to messages
✅ Connected via Studio web interface
✅ Seen real-time collaboration between human and agent

Next Steps

Now that you have the basics working, explore more:

🎓 Learn Core Concepts

Agent Networks - Understanding network architecture
Event System - How agents respond to events
Network Mods - Extending network functionality

📚 Follow Tutorials

Start a Network - Start with a tutorial

🛠️ Advanced Development

Python Interface - Comprehensive API guide
Workspace Interface - File sharing and collaboration
LLM Integration - AI-powered agents

🌟 Examples and Inspiration

Demos - Five demos as part of the tutorials
Example Walkthrough - AI News Chatroom
GitHub Examples - Demos and examples
Discord Community - Connect with other developers

Troubleshooting

Network Won't Start

# Check if ports are in use
lsof -i :8700
lsof -i :8600
 
# Use different ports if needed

Agent Won't Connect

# Verify network is running
curl http://localhost:8700/
 
# Check agent output for error messages

Studio Won't Load

Try a different port for the network:

# Start network on a different port
openagents network start --port 8701
 
# Studio will be available at http://localhost:8050

Success: 🎉 You're now ready to build with OpenAgents! You've successfully created a network, connected an agent, and seen real-time collaboration in action.

Info: Want to go deeper? Check out our Core Concepts to understand how everything works under the hood, or follow our Tutorials for step-by-step guides.