***
title: SignalWire SDKs
subtitle: Install the SDK and build your first application.
description: Everything you need to install the SignalWire SDK, create your first voice AI agent, and connect it to the SignalWire platform.
slug: /
position: 0
max-toc-depth: 3
---------------------
For a complete index of all SignalWire documentation pages, fetch https://signalwire.com/docs/llms.txt
[installation]: /docs/server-sdks/guides/installation
[quick-start]: /docs/server-sdks/guides/quickstart
[development-environment]: /docs/server-sdks/guides/dev-environment
[exposing-agents]: /docs/server-sdks/guides/exposing-agents
## Supported Languages
The SignalWire Server SDK is available in multiple languages. Select the variant that matches your development environment.
## What You'll Learn
This chapter walks you through the complete setup process:
1. **Installation** - Install the SDK and verify it works
2. **Quick Start** - Build your first agent in under 5 minutes
3. **Development Environment** - Set up a professional development workflow
4. **Exposing Your Agent** - Make your agent accessible to SignalWire using ngrok
## Prerequisites
Before starting, ensure you have the following:
| Language | Requirement | Package Manager |
| ---------- | ----------- | --------------- |
| Python | 3.10+ | pip |
| TypeScript | Node.js 18+ | npm |
You'll also need:
* A **terminal/command line** interface
* A **text editor or IDE** (VS Code, etc.)
* (Optional) A **SignalWire account** for testing with real phone calls
## Time to Complete
| Section | Time |
| --------------- | ---------------- |
| Installation | 5 min |
| Quick Start | 5 min |
| Dev Environment | 10 min |
| Exposing Agents | 10 min |
| **Total** | **\~30 minutes** |
## By the End of This Chapter
You will have:
* A working voice AI agent
* Accessible via public URL
* Ready to connect to SignalWire phone numbers
## What is the SignalWire SDK?
The SignalWire SDK lets you create **voice AI agents** - intelligent phone-based assistants that can:
* Answer incoming phone calls automatically
* Have natural conversations using AI
* Execute custom functions (check databases, call APIs, etc.)
* Transfer calls, play audio, and manage complex call flows
* Scale from development to production seamlessly
## How It Works
**The flow:**
1. A caller dials your SignalWire phone number
2. SignalWire requests instructions from your agent (via HTTP)
3. Your agent returns **SWML** (SignalWire Markup Language) - a JSON document describing how to handle the call
4. SignalWire's AI talks to the caller based on your configuration
5. When the AI needs to perform actions, it calls your **SWAIG functions** (webhooks)
6. Your functions return results, and the AI continues the conversation
## Key Concepts
### Agent
An **Agent** is your voice AI application. It's a class that:
* Defines the AI's personality and behavior (via prompts)
* Provides functions the AI can call (SWAIG functions)
* Configures voice, language, and AI parameters
* Runs as a web server that responds to SignalWire requests
```python
from signalwire import AgentBase
class MyAgent(AgentBase):
def __init__(self):
super().__init__(name="my-agent")
# Configure your agent here
```
```typescript
import { AgentBase } from 'signalwire-agents';
const agent = new AgentBase({ name: 'my-agent' });
// Configure your agent here
```
### SWML (SignalWire Markup Language)
**SWML** is a JSON format that tells SignalWire how to handle calls. Your agent generates SWML automatically - you don't write it by hand.
```json
{
"version": "1.0.0",
"sections": {
"main": [
{"answer": {}},
{"ai": {
"prompt": {"text": "You are a helpful assistant..."},
"SWAIG": {"functions": ["..."]}
}}
]
}
}
```
### SWAIG Functions
**SWAIG** (SignalWire AI Gateway) functions are tools your AI can use during a conversation. When a caller asks something that requires action, the AI calls your function.
```python
@agent.tool(description="Look up a customer by phone number")
def lookup_customer(args, raw_data=None):
phone_number = args.get("phone_number", "")
customer = database.find(phone_number)
return FunctionResult(
f"Customer: {customer.name}, Account: {customer.id}"
)
```
```typescript
agent.defineTool({
name: 'lookup_customer',
description: 'Look up a customer by phone number',
parameters: {
phone_number: { type: 'string', description: 'Phone number' }
},
handler: (args) => {
const customer = database.find(args.phone_number);
return new FunctionResult(
`Customer: ${customer.name}, Account: ${customer.id}`
);
},
});
```
## Next Steps
Now that you understand the basics, let's get your development environment set up:
1. [Installation][installation] - Install the SDK
2. [Quick Start][quick-start] - Build your first agent
3. [Development Environment][development-environment] - Professional setup
4. [Exposing Agents][exposing-agents] - Connect to SignalWire