# Token Architecture

***

<figure><img src="/files/QnTJUOPIiVijpsBAEF30" alt=""><figcaption></figcaption></figure>

## CROME Agent Protocol.

The CROME Agent Protocol integrates multiple Ethereum token standards into one cohesive structure, creating highly functional autonomous agents. CAP consists of four clearly defined layers:&#x20;

• **ERC-20 Layer** \[*Fungible Token Layer*]: Defines tokens as fungible and tradable units, enabling seamless exchanges, staking, bridging, and liquidity pools across DeFi ecosystems.&#x20;

• **ERC-721 Layer** \[*Non-Fungible Identity Layer*]: Establishes a unique, non-fungible identity for each token, facilitating individual metadata storage, dedicated logic execution parameters, and precise on-chain identification.&#x20;

• **ERC-6551 Layer** \[*Token-Bound Account Layer*]: Associates each token with a dedicated Token-Bound Account, enabling tokens to manage assets, execute custom logic, and maintain a detailed historical state, autonomously.

• **AI Layer** \[*Autonomous Intelligence Layer]*: Equips each agent with adaptive decision-making capabilities, enabling them to interpret data, adjust behaviours, and coordinate actions autonomously through embedded or connected AI models.

Mathematically, the architecture is represented as:

$$
C = C\_{ERC20} \cup C\_{ERC721} \cup C\_{ERC6551}\cup C\_{AI}
$$

Where:

$$
\begin{array}{ll}
\mathbf{C\_{\text{ERC20}}} & \text{: Fungible, tradable token standard.} \\
\mathbf{C\_{\text{ERC721}}} & \text{: Non-fungible token providing unique identities and metadata.} \\
\mathbf{C\_{\text{ERC6551}}} & \text{: Token-bound account managing programmable logic, assets, and historical state.} \\
\mathbf{C\_{\text{AI}}} & \text{: Intelligence layer for perception, reasoning, adaptation, and multi-agent coordination.}
\end{array}
$$

{% hint style="info" %}
The integration of ERC-20, ERC-721, and ERC-6551 standards empowers each CROME agent with unique capabilities, forming the backbone of decentralized intelligent systems.
{% endhint %}


---

# 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.crome.pro/technical-overview/token-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.