# Quick Start

Build your first AgentKit agent in 5 minutes

URL: https://agentkit.tech/docs/quick-start.mdx

This guide will help you create your first AgentKit agent in under 5 minutes.

## Prerequisites

* Go 1.19 or later
* OpenAI API key (get one at [platform.openai.com](https://platform.openai.com/))

## Step 1: Set up your environment

First, set your OpenAI API key:

```bash
export OPENAI_API_KEY="your-openai-api-key"
```

## Step 2: Create your first agent

Create a new file called `main.go`:

```go
package main

import (
    "context"
    "fmt"
    "log"
    "os"

    "github.com/model-box/agent-kit/agent"
    "github.com/model-box/agent-kit/model"
    "github.com/model-box/agent-kit/session"
)

func main() {
    // Create model
    model := model.Model("gpt-4o").
        SetAPIKey(os.Getenv("OPENAI_API_KEY"))
    
    // Create agent
    ag := agent.New().
        SetModel(model).
        SetSystemPrompt("You are a helpful assistant.")
    
    // Create session and run
    sess := session.New(ag)
    result, err := sess.Run(context.Background(), []agent.ChatMessage{
        agent.NewUserMessage("Hello, world!"),
    }, nil)
    if err != nil {
        log.Fatal(err)
    }
    
    fmt.Println(result.FinalOutput)
}
```

## Step 3: Run your agent

```bash
go run main.go
```

You should see your agent respond to your greeting!

## Step 4: Try a conversation

Let's make it more interactive by adding a simple conversation loop:

```go
package main

import (
    "bufio"
    "context"
    "fmt"
    "log"
    "os"
    "strings"

    "github.com/model-box/agent-kit/agent"
    "github.com/model-box/agent-kit/model"
    "github.com/model-box/agent-kit/session"
)

func main() {
    // Create model
    model := model.Model("gpt-4o").
        SetAPIKey(os.Getenv("OPENAI_API_KEY"))
    
    // Create agent
    ag := agent.New().
        SetModel(model).
        SetSystemPrompt("You are a helpful assistant.")

    // Create a conversation session
    sess := session.New(ag)
    
    fmt.Println("🤖 ChatBot: Hello! I'm your AI assistant. Type 'quit' to exit.")
    
    scanner := bufio.NewScanner(os.Stdin)
    ctx := context.Background()
    
    for {
        fmt.Print("👤 You: ")
        if !scanner.Scan() {
            break
        }
        
        input := strings.TrimSpace(scanner.Text())
        if input == "quit" {
            fmt.Println("🤖 ChatBot: Goodbye!")
            break
        }
        
        if input == "" {
            continue
        }
        
        // Send message to agent
        result, err := sess.Run(ctx, []agent.ChatMessage{agent.NewUserMessage(input)}, nil)
        if err != nil {
            log.Printf("Error: %v", err)
            continue
        }
        
        fmt.Printf("🤖 ChatBot: %s\n\n", result.FinalOutput)
    }
}
```

Run this version to have a back-and-forth conversation with your agent!

## What's Next?

Congratulations! 🎉 You've built your first AgentKit agent. Here's what you can explore next:

### Learn Core Concepts

* [Agents](/agents) - Learn about agent configuration
* [Models](/models) - Explore different model providers
* [Tools](/tools) - Add function calling capabilities
* [Sessions](/sessions) - Manage conversation state

### Follow Guides

* [Multi-turn Conversations](/multi-turn-conversation) - Build persistent conversations
* [Streaming Responses](/streaming-agent) - Add real-time streaming
* [Tool Calling](/tool-calling) - Give agents access to external functions

### Explore Examples

* [Examples](/examples) - See complete working examples
* [GitHub Repository](https://github.com/model-box/agent-kit/tree/main/examples) - More example code

## Need Help?

* 📚 Browse the [documentation](/docs)
* 💬 Join our [GitHub Discussions](https://github.com/model-box/agent-kit/discussions)
* 🐛 Report issues on [GitHub Issues](https://github.com/model-box/agent-kit/issues)