> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agenite.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Quick start

> Get started with Agenite in minutes

## Installation

First, install Agenite's core packages:

<CodeGroup>
  ```bash npm theme={null}
  npm install @agenite/agent @agenite/tool
  ```

  ```bash pnpm theme={null}
  pnpm add @agenite/agent @agenite/tool
  ```

  ```bash yarn theme={null}
  yarn add @agenite/agent @agenite/tool
  ```
</CodeGroup>

Then install your preferred LLM provider:

<CodeGroup>
  ```bash AWS Bedrock theme={null}
  npm install @agenite/bedrock
  ```

  ```bash Ollama theme={null}
  npm install @agenite/ollama
  ```
</CodeGroup>

<Note>
  For AWS Bedrock, make sure you have AWS credentials configured. For Ollama, ensure you have it [installed and running locally](https://ollama.ai).
</Note>

## Building tools

Tools are the building blocks that give your agent abilities to perform tasks. While we'll start with a simple calculator example below, you can build much more meaningful tools like:

* Database query tools for data analysis
* API integration tools for external services
* File system tools for document processing
* Custom business logic tools for your domain

Let's start with a basic example:

<CodeGroup>
  ```typescript AWS Bedrock theme={null}
  import { Agent } from '@agenite/agent';
  import { Tool } from '@agenite/tool';
  import { BedrockProvider } from '@agenite/bedrock';
  import { prettyLogger } from '@agenite/pretty-logger';

  // Create a calculator tool
  const calculatorTool = new Tool<{ expression: string }>({
    name: 'calculator',
    description: 'Perform basic math operations',
    inputSchema: {
      type: 'object',
      properties: {
        expression: { type: 'string' },
      },
      required: ['expression'],
    },
    execute: async ({ input }) => {
      try {
        const result = new Function('return ' + input.expression)();
        return { isError: false, data: result.toString() };
      } catch (error) {
        if (error instanceof Error) {
          return { isError: true, data: error.message };
        }

        return { isError: true, data: 'Unknown error' };
      }
    },
  });

  // Create an agent
  const agent = new Agent({
    name: 'math-buddy',
    provider: new BedrockProvider({
      model: 'anthropic.claude-3-5-sonnet-20240620-v1:0',
    }),
    tools: [calculatorTool],
    instructions: 'You are a helpful math assistant.',
    middlewares: [prettyLogger()],
  });

  // Example usage
  const result = await agent.execute({
    messages: [
      {
        role: 'user',
        content: [{ type: 'text', text: 'What is 1234 * 5678?' }],
      },
    ],
  });

  ```

  ```typescript Ollama theme={null}
  iimport { Agent } from '@agenite/agent';
  import { Tool } from '@agenite/tool';
  import { OllamaProvider } from '@agenite/ollama';
  import { prettyLogger } from '@agenite/pretty-logger';

  // Create a calculator tool
  const calculatorTool = new Tool<{ expression: string }>({
    name: 'calculator',
    description: 'Perform basic math operations',
    inputSchema: {
      type: 'object',
      properties: {
        expression: { type: 'string' },
      },
      required: ['expression'],
    },
    execute: async ({ input }) => {
      try {
        const result = new Function('return ' + input.expression)();
        return { isError: false, data: result.toString() };
      } catch (error) {
        if (error instanceof Error) {
          return { isError: true, data: error.message };
        }

        return { isError: true, data: 'Unknown error' };
      }
    },
  });

  // Create an agent
  const agent = new Agent({
    name: 'math-buddy',
    provider: new OllamaProvider({
      model: 'llama3.2',
    }),
    tools: [calculatorTool],
    instructions: 'You are a helpful math assistant.',
    middlewares: [prettyLogger()],
  });

  // Example usage
  const result = await agent.execute({
    messages: [
      {
        role: 'user',
        content: [{ type: 'text', text: 'What is 1234 * 5678?' }],
      },
    ],
  });

  ```
</CodeGroup>

### Sample output

When you run the code above, you'll see nicely formatted output in your console thanks to the prettyLogger:

<img src="https://mintcdn.com/agenite/KlgXSqKpWDo_NGNz/images/quick-start/output.png?fit=max&auto=format&n=KlgXSqKpWDo_NGNz&q=85&s=017326ee14b5898ee607c6ee4e29a8a8" alt="Sample output" width="1494" height="1144" data-path="images/quick-start/output.png" />

<Note>
  The pretty logger is handy for debugging, but you can use any logger you want and or not use it at all.
</Note>

## Next steps

<CardGroup cols={2}>
  <Card title="Core concepts" icon="book" href="/core-concepts/overview">
    Learn about agents, tools, and providers in depth
  </Card>

  <Card title="Examples" icon="code" href="/examples">
    Explore more complex examples and use cases
  </Card>
</CardGroup>