# Core Architecture: Hub-and-Spoke

The bitGPT Network is built on a **hub-and-spoke architecture**, a design that elegantly balances centralized power with decentralized efficiency. Imagine a bustling city where the central hub acts as the heartbeat, managing heavy lifting tasks like model training and data processing. The spokes, spread out across the city, are the edge devices — your smartphones, computers, tablets — handling local AI operations. This setup ensures that while the hub takes care of the intensive work, your device keeps your data private and processes AI tasks locally, reducing latency and enhancing security.

**Hubs** are the nerve centers of the network, comprising sponsors, curators, proxy operators, and engineers. They form the infrastructural and governance backbone, orchestrating resource allocation and ensuring the network operates smoothly. **Spokes**, on the other hand, are the edge devices where AI agents are deployed, powered by SLMs. These spokes deliver a self-sovereign AI experience, allowing users to maintain control over their data and computations.

<figure><img src="/files/xEz9MBQPe386Z5zZXGSp" alt=""><figcaption><p>Network Architecture</p></figcaption></figure>

This architecture isn't just about efficiency; it's a strategic move towards decentralization. By distributing computational tasks between hubs and spokes, the network avoids the pitfalls of centralization, like single points of failure and data breaches. It’s a symphony where each part plays its role, ensuring the network is both powerful and resilient.

The hub-and-spoke topology delivers substantive benefits that enhance both individual user experience and broader ecosystem sustainability. From a computational efficiency perspective, users experience markedly reduced latency for routine AI operations through edge processing on spokes. The architecture also catalyzes powerful network effects through its unique structure. Each additional spoke node contributes to the network’s collective intelligence through privacy-preserving federated learning, enhancing model performance without compromising individual data sovereignty.

The hub coordination layer facilitates efficient resource discovery and allocation, optimizing utility for both resource providers and consumers. These dynamics create a self-reinforcing cycle where enhanced user experience strengthens network effects and amplifies system utility, addressing both immediate user requirements and long-term ecosystem sustainability imperatives.


---

# 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://bitgpt-2.gitbook.io/docs/infrastructure/core-architecture-hub-and-spoke.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.