> ## 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.

# Introduction

> A modern, modular, and type-safe framework for building AI agents using typescript

<img className="block dark:hidden" src="https://mintcdn.com/agenite/KlgXSqKpWDo_NGNz/images/hero-light.png?fit=max&auto=format&n=KlgXSqKpWDo_NGNz&q=85&s=f5295c648033db8c7c1eda2190220e03" alt="Hero Light" width="2475" height="1576" data-path="images/hero-light.png" />

<img className="hidden dark:block" src="https://mintcdn.com/agenite/KlgXSqKpWDo_NGNz/images/hero-dark.png?fit=max&auto=format&n=KlgXSqKpWDo_NGNz&q=85&s=cbc800f72d4720c221540ae46b325af2" alt="Hero Dark" width="2475" height="1576" data-path="images/hero-dark.png" />

## What is Agenite?

Agenite is a powerful TypeScript framework designed for building sophisticated AI agents. It provides a modular, type-safe, and flexible architecture that makes it easy to create, compose, and control AI agents with advanced capabilities.

<Note>
  The name Agenite (pronounced as Agen-ite) comes from combining "Agent" with the suffix "-ite", representing a framework that crystallizes best practices for building AI agents.
</Note>

### Key features

<AccordionGroup>
  <Accordion title="Type safety and developer experience" icon="shield-check">
    * Built from the ground up with TypeScript
    * Robust type checking for tools and agent configurations
    * Excellent IDE support and autocompletion
  </Accordion>

  <Accordion title="Tool integration" icon="wrench">
    * First-class support for function calling
    * Built-in JSON Schema validation
    * Structured error handling
    * Easy API integration
  </Accordion>

  <Accordion title="Provider agnostic" icon="plug">
    * Support for AWS Bedrock and Ollama
    * Consistent interface across providers
    * Easy extension for new providers
  </Accordion>

  <Accordion title="Advanced architecture" icon="cube">
    * Bidirectional flow using JavaScript generators
    * Step-based execution model
    * Built-in state management with reducers
    * Flexible middleware system
  </Accordion>

  <Accordion title="Model context protocol (MCP)" icon="brain">
    * Standardized protocol for connecting LLMs to data sources
    * Client implementation for interacting with MCP servers
    * Access to web content, filesystem, databases, and more
    * Similar to how USB-C provides universal hardware connections
  </Accordion>
</AccordionGroup>

## Core concepts

### Agents

Agents are the central building blocks in Agenite. An agent:

* Orchestrates interactions between LLMs and tools
* Manages conversation state and context
* Handles tool execution and results
* Supports nested execution for complex workflows
* Provides streaming capabilities for real-time interactions

### Tools

Tools extend agent capabilities by providing specific functionalities:

* Strong type safety with TypeScript
* JSON Schema validation for inputs
* Flexible error handling
* Easy API integration

### Providers

Currently supported LLM providers:

* AWS Bedrock with Claude models
* Local models via Ollama
* Consistent interface for easy provider switching
* Built-in streaming support

## Available packages

Agenite is organized into several modules that you can install based on your needs:

### Core packages

These are the essential packages for building agents with Agenite.

<CardGroup cols={3}>
  <Card title="@agenite/agent">
    Core agent library for orchestrating LLMs and tools

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

  <Card title="@agenite/tool">
    Tool interface for extending agent capabilities

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

  <Card title="@agenite/llm">
    LLM abstraction layer and utilities

    ```bash theme={null}
    npm install @agenite/llm
    ```
  </Card>
</CardGroup>

### Provider packages

Choose one or more provider packages based on the LLMs you want to use.

<CardGroup cols={2}>
  <Card title="@agenite/openai">
    OpenAI API provider (GPT models)

    ```bash theme={null}
    npm install @agenite/openai
    ```
  </Card>

  <Card title="@agenite/anthropic">
    Anthropic API provider (Claude models)

    ```bash theme={null}
    npm install @agenite/anthropic
    ```
  </Card>

  <Card title="@agenite/bedrock">
    AWS Bedrock provider (Claude, Titan models)

    ```bash theme={null}
    npm install @agenite/bedrock
    ```
  </Card>

  <Card title="@agenite/ollama">
    Ollama provider for local models

    ```bash theme={null}
    npm install @agenite/ollama
    ```
  </Card>
</CardGroup>

### MCP package

Integration with the Model Context Protocol (MCP) for standardized data access.

<CardGroup cols={1}>
  <Card title="@agenite/mcp">
    Client implementation for interacting with MCP servers to access external data sources

    ```bash theme={null}
    npm install @agenite/mcp
    ```
  </Card>
</CardGroup>

### Middleware packages

Optional packages for enhancing agent functionality.

<CardGroup cols={1}>
  <Card title="@agenite/pretty-logger" href="/packages/pretty-logger">
    Colorful console logging for agent execution

    ```bash theme={null}
    npm install @agenite/pretty-logger
    ```
  </Card>
</CardGroup>

## Typical installation

For a basic setup with OpenAI:

```bash theme={null}
npm install @agenite/agent @agenite/tool @agenite/llm @agenite/openai
```

For AWS Bedrock with optional pretty logging:

```bash theme={null}
npm install @agenite/agent @agenite/tool @agenite/llm @agenite/bedrock @agenite/pretty-logger
```

## Next steps

<Steps>
  <Step title="Install Agenite">
    Start by installing the core packages and your preferred provider:

    ```bash theme={null}
    npm install @agenite/agent @agenite/tool
    npm install @agenite/bedrock # For AWS Bedrock
    # OR
    npm install @agenite/ollama  # For local models
    ```
  </Step>

  <Step title="Learn the basics">
    Follow our [Quick start guide](/quickstart) to create your first agent
  </Step>

  <Step title="Explore examples">
    Check out our [Examples](/examples) to see Agenite in action
  </Step>

  <Step title="Build something amazing">
    Use our [API reference](/api-reference/agent) to build your own AI agents
  </Step>
</Steps>

<CardGroup cols={2}>
  <Card title="Quick start guide" icon="rocket" href="/quickstart">
    Create your first agent in minutes with our step-by-step guide
  </Card>

  <Card title="Core concepts" icon="book" href="/core-concepts/overview">
    Deep dive into agents, tools, and the execution model
  </Card>
</CardGroup>