# Technical Architecture

<figure><img src="/files/HVkmtnkwQIxkfGL2hEwj" alt=""><figcaption></figcaption></figure>

### Equinox AI is structured as a high-performance, multi-layered infrastructure engineered to correlate blockchain behaviour with decentralised social activity in near real-time. Each layer of the system is designed with performance, modularity, and privacy-control in mind, allowing us to deliver complex behavioural data in a clean and queryable format.

***

#### System Overview

```
[Data Collection Layer] → [Processing Layer] → [Analysis Layer] → [Data Serving Layer] → [Interface Layer]
```

***

#### 1. Data Collection Layer

This is the backbone of Equinox AI. The platform continuously ingests:

• **On-chain Data**: Multichain RPC and WebSocket-based transaction fetchers with native indexing for Ethereum, BSC, and L2s.\
• **Off-chain Data**: Scraping bots for Telegram groups, public X accounts, Discord servers, GitHub activity, and web2 endpoints.\
• **Storage**: Raw logs are time-stamped, hashed, and tagged by data type before being pushed to a distributed data lake.

***

#### 2. Processing Layer

At this layer, raw inputs are transformed into usable records:

• **Data Normalisation**: Converts blockchain logs and social data into a unified schema.\
• **Linkage Engine**: Detects alias overlaps across usernames, wallets, and public messages.\
• **Sequencer**: Arranges token flows, mixer hops, bridge routes, and social events in chronological trails.

***

#### 3. Analysis Layer

Here, the intelligence begins to form:

• **Pattern Recognition**: Machine learning models that score social-financial behaviour.\
• **Entity Grouping**: Clustering based on shared wallets, post timing, or trading behaviour.\
• **Custom Alerts**: Developer-tunable rules for behavioural thresholds, flagging, and risk scoring.

***

#### 4. Data Serving Layer

All computed data is served through structured access:

• **Caching Engine**: Reduces latency for common wallet or group queries.\
• **Graph DBs**: Stores social–wallet–token links in a retrievable graph structure.\
• **Rate-Limited API**: Ensures equitable bandwidth distribution for dApp, partners, and backend tooling.

***

#### 5. Interface Layer

The visible layer of Equinox:

• **Equinox dApp**: Web interface to explore analytics, scan identities, and monitor wallets.\
• **Builder Portal**: Advanced toolkit with custom API generation, report exports, and SDKs.\
• **Partner Tools**: Access modules for analysts, security auditors, and exchanges.

***

#### Smart Contract Stack

```solidity
• ENOX Token: ERC-20, with built-in burn hooks for cloaking behaviour.
• Opt-Out Contract: burn-to-delist feature with Merkle root tracking for accountability.
• Billing Mechanism: optional fee model for third-party API calls and integrations.
```

***

#### Tech Stack Summary Table

| Layer             | Tech Used                                     |
| ----------------- | --------------------------------------------- |
| Blockchain Access | Alchemy, Infura, QuickNode, custom RPC relays |
| Social Indexing   | Python, Puppeteer, Selenium, NodeJS           |
| Analysis Engine   | Python (Pandas, NumPy, Scikit), Rust, Jupyter |
| Frontend          | React, Tailwind, Next.js, WebSockets          |
| Backend API       | FastAPI, PostgreSQL, Redis, TimescaleDB       |
| Infra             | Docker, Kubernetes, NGINX, Cloudflare, S3     |

***

**Equinox AI's architecture is purpose-built to evolve with the ecosystem. As new dApps, bridges, chains, or communication platforms emerge, our plug-and-play design ensures they can be integrated with minimal downtime and no overhaul. This foundation supports future upgrades such as ZK-layer enhancements, wallet fingerprinting, and advanced wallet–social trust scoring models.**


---

# 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://equinoxai.gitbook.io/equinox-ai-whitepaper/architecture-and-technology/technical-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.