# ElizaOS

## About

[ElizaOS](https://eliza.how/docs/intro) is a powerful multi-agent simulation framework designed to create, deploy, and manage autonomous AI agents. Built with TypeScript, it provides a flexible and extensible platform for developing intelligent agents that can interact across multiple platforms while maintaining consistent personalities and knowledge.

## Installation

1. Install `bun` и `Node.js` (v18+)
2. Clone the repo and run:

```bash
git clone <https://github.com/elizaos/eliza-starter.git> 
cd eliza-starter 
cp .env.example .env 
bun i && bun run build && bun start
```

You can find more details in the [official documentation](https://eliza.how/docs/intro#installation).

## How to Use AIML API via ElizaOS

1. Define your [AIMLAPI key](https://aimlapi.com/app/keys) and other environment variables:

```bash
AIMLAPI_API_KEY=sk-***
AIMLAPI_SMALL_MODEL=openai/gpt-3.5-turbo
AIMLAPI_MEDIUM_MODEL=anthropic/claude-3-5-sonnet-20240521-v2:0
AIMLAPI_LARGE_MODEL=google/gemini-2.0-pro
```

2. Configure your character in the `character.json` file as follows:

```json
{
  "modelProvider": "aimlapi",
  "settings": {
    "model": "gpt-4",
    "maxInputTokens": 200000,
	...
  }
}
```

ElizaOS provides a UI at <http://localhost:3000>. Each configured character appears as a separate conversation partner in the left-hand panel:

<figure><img src="/files/I3rTaSY86He4oEiQvKdx" alt=""><figcaption></figcaption></figure>

Click the small speaker icon below any message to hear it read aloud:

<figure><img src="/files/zVsqAsvWHj3CQ5qAEmJg" alt=""><figcaption></figcaption></figure>

## Our Supported Models

In the environment variables for ElizaOS, you can specify almost any of our [text models](/api-references/text-models-llm.md#complete-text-model-list), including:

* OpenAI ChatGPT ([openai/gpt-3.5-turbo](/api-references/text-models-llm/openai/gpt-3.5-turbo.md), [gpt-4-turbo](/api-references/text-models-llm/openai/gpt-4-turbo.md), ...),
* Google Gemini ([google/gemini-2.0-flash](/api-references/text-models-llm/google/gemini-2.0-flash.md), ...)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.aimlapi.com/integrations/elizaos.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.