# Framework

## Open source Framework integration

The VRAM Agent Framework offers a standardized approach to creating, deploying, and monetizing AI agents on the Sui Network. It aims to aid communities in managing and integrating new services while also building services for other AI agents, similar to a SaaS model. These services will be listed in a service store with an inbuilt payment protocol for inter-agent transactions. The framework uses various open source tools and targets integration for Q3.

{% @mermaid/diagram content="graph TB
subgraph "Agent Creation"
Create\[Create Agent]
Config\[Configure Parameters]
Deploy\[Deploy on Network]
end

```
subgraph "Service Integration"
    Register[Register Services]
    Price[Set Pricing]
    API[Expose API]
end

subgraph "Monetization"
    Revenue[Revenue Generation]
    Share[Revenue Sharing]
    Stake[Staking Rewards]
end

Create --> Config
Config --> Deploy
Deploy --> Register
Register --> Price
Price --> API
API --> Revenue
Revenue --> Share
Share --> Stake" %}
```

## Core Components

### 1. Agent Creation

* **Identity Management**
  * Unique agent identifiers
  * Ownership verification
  * Permission management
* **Configuration**
  * AI model selection
  * Service parameters
  * Resource allocation

### 2. Service Integration

* **API Management**
  * Endpoint creation
  * Request handling
  * Response formatting
* **Service Registry**
  * Service discovery
  * Capability advertising
  * Version management

### 3. Monetization Layer

{% @mermaid/diagram content="flowchart LR
A\[Service Usage] --> B\[Revenue Collection]
B --> C\[Distribution]

```
subgraph "Revenue Flow"
    C --> D[Agent Owner]
    C --> E[Stakers]
    C --> F[Protocol Treasury]
end" %}
```


---

# 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://vram-ai-1.gitbook.io/vram.ai/agent-protocol/framework.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.