# Two-Layer Architecture

AGOS Cloud consists of two distinct layers that work together.

## Layer 1: AGOS Cloud Platform

**URL**: `claw.agos.fun`

The platform where you:

* Connect your Web3 wallet
* Deposit stablecoins for AIOU
* Create and manage agents
* View billing and transaction history

### Key Functions

| Function              | Description                        |
| --------------------- | ---------------------------------- |
| **Wallet Management** | View AIOU balance, deposit USDT    |
| **Agent Management**  | Create, start, stop, delete agents |
| **Funding**           | Transfer AIOU to agent wallets     |
| **Monitoring**        | View agent status and costs        |

### Navigation

```
Dashboard      → Overview of all agents
Agents         → List and manage agents
LLM API        → API endpoint and pricing
Deposits       → Add funds (USDT → AIOU)
History        → Transaction records
Billing        → Cost breakdown
```

## Layer 2: OpenClaw Agent Dashboard

**URL**: `https://{agent-id}.agent.agos.fun`

Each agent has its own dedicated control panel for:

* Chatting with the agent directly
* Configuring channels (Telegram, Discord)
* Installing skills
* Viewing logs and usage

### Key Functions

| Function      | Description                           |
| ------------- | ------------------------------------- |
| **Chat**      | Direct conversation with your agent   |
| **Channels**  | Connect messaging platforms           |
| **Skills**    | Install and manage agent capabilities |
| **Cron Jobs** | Schedule automated tasks              |
| **Usage**     | Monitor resource consumption          |
| **Logs**      | Debug and troubleshoot                |

### Navigation

```
Chat           → Direct messaging
Overview       → Agent status
Channels       → Telegram, Discord, etc.
Instances      → Deployment status
Sessions       → Active conversations
Usage          → Resource metrics
Cron Jobs      → Scheduled tasks
Agents         → Sub-agents (if any)
Skills         → Installed capabilities
Nodes          → Connected devices
Config         → Environment variables
Debug          → Diagnostic tools
Logs           → System logs
Resources      → File system access
Docs           → Agent documentation
```

## How They Connect

```
┌─────────────────────────────────────┐
│     AGOS Cloud Platform               │
│     (claw.agos.fun)                 │
│                                     │
│  • Create agent                     │
│  • Fund with AIOU                   │
│  • View costs                       │
└──────────────┬──────────────────────┘
               │ Deploys to
               ▼
┌─────────────────────────────────────┐
│     OpenClaw Agent Dashboard        │
│     ({agent}.agent.agos.fun)        │
│                                     │
│  • Chat with agent                  │
│  • Configure channels               │
│  • Install skills                   │
│  • View logs                        │
└─────────────────────────────────────┘
```

## User Journey

1. **Platform** - Create and fund an agent
2. **Agent Dashboard** - Configure and interact with the agent
3. **Platform** - Monitor costs, add funds as needed

## Access Methods

| Layer                   | Access Via                       |
| ----------------------- | -------------------------------- |
| **AGOS Cloud Platform** | Web browser + Web3 wallet        |
| **Agent Dashboard**     | Web browser (auto-authenticated) |
| **Agent VPS**           | SSH (credentials provided)       |

## Next Steps

→ [Deploy Your First Agent](/agos/agos-cloud/quickstart/deploy-agent.md) to see both layers in action


---

# 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://agos.gitbook.io/agos/agos-cloud/concepts/architecture.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.