> For the complete documentation index, see [llms.txt](https://docs.guayaba.run/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.guayaba.run/getting-started.md).

# Getting Started

## Create your first agent

**\~5 minutes. Result:** a running agent connected to Telegram.

### Before you start

You need credits before deploying. Go to **Profile → Buy AI Credits** and purchase a pack.

***

{% stepper %}
{% step %}

### Infrastructure

Click **Create Agent** in the sidebar.

**Deployment Region** — choose the region closest to your users.

| Region       | Location    |
| ------------ | ----------- |
| US West      | Oregon      |
| US East      | N. Virginia |
| EU West      | Dublin      |
| EU Central   | Frankfurt   |
| Asia Pacific | Singapore   |

**Hardware Resources** — defaults work for most agents.

| Resource     | Default  |
| ------------ | -------- |
| CPU          | 0.5 Core |
| Disk Storage | 5 GB     |
| Memory (RAM) | 4 GB     |
| GPU          | None     |

> Higher tiers coming soon.

Click **Continue**.
{% endstep %}

{% step %}

### Framework

Select the **framework you want to use.** 

Click **Continue**.
{% endstep %}

{% step %}

### Agent Configuration

#### Identity

| Field | Required | Notes                                |
| ----- | -------- | ------------------------------------ |
| Name  | ✅        | Display name                         |
| Bio   | ✅        | Purpose and identity (max 500 chars) |

#### Personality

**Additional Instructions** — system-level directives appended after core config.

```
Always cite sources when sharing facts.
Never use informal language with users.
```

**Seed Knowledge** — upload PDF or TXT files to inject into long-term memory on first boot.

#### Model

**Thinking Level**

| Level  | Best for           |
| ------ | ------------------ |
| Off    | Simple Q\&A        |
| Low    | General assistants |
| Medium | Most use cases     |
| High   | Complex tasks      |

**Included Capabilities — always active**

| Capability          | Description                         |
| ------------------- | ----------------------------------- |
| Web Search          | Real-time web search                |
| Web Fetch           | Read content from any URL           |
| Image Understanding | Analyze images from users           |
| File Access         | Read/write files in agent workspace |

#### Communication Channels

Enable **Telegram** and paste your bot token.

> Need a token? See [Telegram](#telegram).

#### Review

Review full configuration and click **Create Agent**.
{% endstep %}
{% endstepper %}

***

### Your agent is running

Status: **Pending** → **Running**

| Action | Description                      |
| ------ | -------------------------------- |
| Logs   | Real-time runtime activity       |
| Files  | Files in the agent's workspace   |
| Edit   | Modify configuration at any time |
| Stop   | Pause the agent and free compute |


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.guayaba.run/getting-started.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.