# Architecture

By leveraging blockchain, cryptography, LLMs, and edge computing technologies, **Neuro Net** significantly enhances the security, efficiency, and scalability of AI agent services, in a decentralized environment.

<figure><img src="/files/2nr739SreTKzY3fDJaAW" alt=""><figcaption></figcaption></figure>

**Neuro Net** is composed of the following key modules:

* **AIDA(AI Data Availability) Layer**: Ensures the availability of AI agents by providing robust services for querying, managing, and using AI Agents, as well as offering scalability and composability.
* **L2 Blockchain**: Used for deploying and running decentralized AI applications(AI-Dapps), and provides crypto-native capabilities like smart contracts (compatible with EVM, SVM) and oracles.
* **AI Agent Creator Platform**: Provides tools for AI Agent creators, including development tools and deployment toolchains. We will also integrate existing AI agent tools such as dify.ai, coze.com, langchain, etc.
* [**DePIN Connector**](/neuro-net/depin-connector.md): Natively integrates with DePIN, allowing decentralized access to external data interfaces to gather various forms of external feedback.
  * **Storage Module**: Offers storage facilities supporting SQL, NoSQL, vector databases, Filecoin, Arweave, etc, which can be used for external knowledge bases and memories.
  * **Computing Power Module**: Integrates existing decentralized computational power networks such as [io.net](https://io.net) and [Aethir](https://aethir.com), and supports efficient and economical model training, fine-tuning, and inference.
  * **Physical Data Module:** Integrates with real-time physical data sources such as temperature, acceleration, location, and health metrics, allowing AI agents to interact and respond dynamically.
* [**Knowledge Base**](/neuro-net/ai-creator-platform/g-kb-gonesis-knowledge-base.md)**:** Provides high reliablity, unlimited external knowledge base extensions for AI agents, with privacy protection.


---

# 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.gonesis.ai/neuro-net/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.