### Project Setup and Execution

Source: https://github.com/wladpaiva/aibitat/blob/main/README.md

Instructions for setting up the project and running examples. This involves installing dependencies using Bun and executing example scripts.

```bash
bun install
```

```bash
bun run examples/beginner-chat.ts
```

--------------------------------

### Install AIbitat with Bun

Source: https://github.com/wladpaiva/aibitat/blob/main/README.md

Steps to set up a new project using Bun, install the AIbitat package, and configure the OpenAI API key.

```bash
mkdir my-project
cd my-project
bun init
bun install aibitat

# Create .env file with your API key
OPENAI_API_KEY=...
```

--------------------------------

### Basic AIbitat Usage Example

Source: https://github.com/wladpaiva/aibitat/blob/main/README.md

A TypeScript example demonstrating how to create an AIbitat instance, define agents with roles, set up a channel, and start a conversation.

```typescript
import {AIbitat} from 'aibitat'
import {cli} from 'aibitat/plugins'

const aibitat = new AIbitat()
  .use(cli())
  .agent('client', {
    interrupt: 'ALWAYS',
    role: 'You are a human assistant. Reply "TERMINATE" when there is a correct answer or there`s no answer to the question.',
  })
  .agent('mathematician', {
    role: `You are a Mathematician and only solve math problems from @client`,
  })
  .agent('reviewer', {
    role: `You are a Peer-Reviewer and you do not solve math problems. 
    Check the result from @mathematician and then confirm. Just confirm, no talk.`,
  })
  .channel('management', ['mathematician', 'reviewer', 'client'])

// aibitat.onMessage(console.log)

await aibitat.start({
  from: 'client',
  to: 'management',
  content: 'How much is 2 + 2?',
})

console.log(aibitat.chats)
```

--------------------------------

### Create Custom Plugins

Source: https://github.com/wladpaiva/aibitat/blob/main/README.md

Provides a template for creating custom AIbitat plugins. A plugin is defined as a function returning an object implementing the `AIbitatPlugin` interface, which includes a `name` and a `setup` method. The `setup` method receives the AIbitat instance and can register event listeners or add new functionality.

```typescript
import {AIbitatPlugin} from 'aibitat'

export function myPlugin(): AIbitatPlugin {
  return {
    name: 'my-plugin',
    setup(aibitat) {
      console.log(`setting up my plugin`)

      aibitat.onMessage(({from, to, content}) => {
        console.log(`${from}: ${content}`)
      })
    },
  }
}
```

--------------------------------

### AIbitat Constructor Configuration

Source: https://github.com/wladpaiva/aibitat/blob/main/README.md

Details the default configuration options for the AIbitat constructor, including providers, models, and conversation settings.

```APIDOC
new AIbitat(config)
  - Creates a new AIbitat instance.
  - The `config` object can be used to configure the instance.
  - By default, aibitat uses **OpenAI** and **GPT-3.5-TURBO** as the provider for the conversation and **GPT-4** for predicting the next agent to speak.
  - You can change it by passing `provider` and `model` to the `AIbitat` constructor or by setting them on the specific agent/channel config.

  Default config:
  {
    providers: 'openai',
    model: 'gpt-3.5-turbo',
    interrupt: 'NEVER',
    maxRounds: 100,
    chats: [
      // { from: '🧑', to: '🤖', content: `Talk about something`, state: 'success' },
    ]
  }

.agent(name, config)
  - Creates a new agent.
  - The `config` object can be used to configure the agent.
  - By default, agents use the `interrupt` from the `AIbitat` config.

.channel(name, agents, config)
  - Creates a new channel.
  - The `config` object can be used to configure the channel.
  - By default, `maxRounds` is set to `100`.
```

--------------------------------

### Use Built-in Plugins

Source: https://github.com/wladpaiva/aibitat/blob/main/README.md

Illustrates how to extend AIbitat's capabilities by using built-in plugins. The `cli()` plugin adds CLI interaction, while others like `fileHistory` and `experimental_webBrowsing` offer additional features.

```typescript
import {cli} from 'aibitat/plugins'

const aibitat = new AIbitat().use(cli())
```

--------------------------------

### Define and Use Functions

Source: https://github.com/wladpaiva/aibitat/blob/main/README.md

Demonstrates how to define functions for AIbitat agents to execute. Functions are registered with a name, description, parameters, and an asynchronous handler. The function name must be added to the agent's configuration to be callable.

```typescript
const aibitat = new AIbitat()
  .agent('...', {functions: ['doSomething']})
  .function({
    name: 'doSomething',
    description: 'Let me do something for you.',
    parameters: {
      type: 'object',
      properties: {},
    },
    async handler() {
      return '...'
    },
  })
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.