> ## Documentation Index
> Fetch the complete documentation index at: https://whitepaper.neurobro.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Technical Architecture

> Detailed technical overview of the Neurobro Terminal system

<Frame>
  <img src="https://mintcdn.com/neurobro/snf_UApj-RJvGVcR/images/architecture.webp?fit=max&auto=format&n=snf_UApj-RJvGVcR&q=85&s=a1669ca561f14d430dd968e2bd833688" style={{ borderRadius: '0.5rem' }} width="4288" height="2258" data-path="images/architecture.webp" />
</Frame>

## Introduction

At Neurobro, we aim to build the new standard for AI information in crypto. This goal comes hand in hand with the excellence of the platform and implementation of real tech.

## Platform Microservices Architecture

The Neurodex Platform comprises four primary services:

<CardGroup cols={2}>
  <Card title="UI (Client)" icon="window">
    Next.js frontend for user interactions
  </Card>

  <Card title="Backend (API)" icon="server">
    FastAPI service for request handling
  </Card>

  <Card title="Neurobro Agents" icon="robot">
    Core intelligence service
  </Card>

  <Card title="Background Services" icon="signal">
    Background workers to keep the platform running smoothly
  </Card>
</CardGroup>

Together, they form the platform, which allows real-time tracking of the market, data processing, analysis, and keeping it up to date, agent coordination, application layer with backend/client, databases, and more.

## Underlying Services

Here's the list of the underlying services, which make the platform work:

<CardGroup cols={3}>
  <Card title="Relational Database" icon="database">
    PostgreSQL + PgBouncer
  </Card>

  <Card title="Document Database" icon="database">
    MongoDB
  </Card>

  <Card title="Cache" icon="bolt">
    Redis
  </Card>

  <Card title="Vector Store" icon="network-wired">
    Qdrant
  </Card>

  <Card title="Graph Database" icon="database">
    Neo4j
  </Card>

  <Card title="SSL security" icon="shield-check">
    HTTPS via Let's Encrypt and Traefik
  </Card>

  <Card title="CDN" icon="globe">
    Cloudflare
  </Card>

  <Card title="Error Tracking" icon="bug">
    Sentry
  </Card>

  <Card title="Analytics" icon="chart-line">
    PostHog + Google Analytics
  </Card>

  <Card title="Monitoring" icon="gauge">
    Prometheus + Loki + Grafana + Opentelemetry + Alertmanager
  </Card>

  <Card title="Deployment" icon="rocket">
    Docker + Kubernetes
  </Card>
</CardGroup>

## Web Application Architecture

<AccordionGroup>
  <Accordion icon="window" title="UI (Frontend)">
    <CardGroup cols={2}>
      <Card title="Framework" icon="react">
        Next.js with SSR optimization
      </Card>

      <Card title="Authentication" icon="shield-check">
        Neurobro Pass (Google, Apple, Email OTP)
      </Card>

      <Card title="Swaps" icon="swap">
        Rango Exchange API integration
      </Card>
    </CardGroup>

    The main focus is on the simplicity and usability of the client. We pay attention to the UI/UX and always iterate to make it better.
  </Accordion>

  <Accordion icon="server" title="Backend (API)">
    <Tabs>
      <Tab title="Core Features">
        * FastAPI
        * Database layer
        * Message routing
        * Major services integration
      </Tab>

      <Tab title="Integrations">
        <CardGroup cols={4}>
          <Card title="Storage" icon="database">
            PostgreSQL
          </Card>

          <Card title="Document DB" icon="database">
            MongoDB
          </Card>

          <Card title="Cache" icon="bolt">
            Redis
          </Card>

          <Card title="Subscriptions" icon="credit-card">
            Stripe + RevenueCat
          </Card>
        </CardGroup>
      </Tab>
    </Tabs>

    The backend is responsible for the core functionality of the platform. It handles the requests from the client, processes the data, and simply connects all the services together.
  </Accordion>

  <Accordion icon="robot" title="Neurobro Agents">
    * Containerized replicas
    * Workflow-based execution
    * Real-time streaming
    * Nevrons orchestration

    <Tabs>
      <Tab title="Nevrons Overview">
        There are 200+ Nevrons (swarm AI Agents) in total, each with a unique purpose and set of tools. Here are some examples:

        <CardGroup cols={2}>
          <Card title="Market Analysis" icon="chart-line">
            nevron23-26 - Market Sentiment Analysis
          </Card>

          <Card title="Technical Analysis" icon="chart-simple">
            nevron31-33 - Technical Analysis
          </Card>

          <Card title="Research" icon="magnifying-glass">
            nevron12-17 - Project Research (Focus on web, official data, publications, etc.)
          </Card>

          <Card title="On-Chain Scam Detection" icon="database">
            nevron77 - On-Chain scam detection (Focus on suspicious onchain activity)
          </Card>
        </CardGroup>
      </Tab>
    </Tabs>
  </Accordion>

  <Accordion icon="signal" title="Background Services">
    <Tabs>
      <Tab title="Core Features">
        * Background workers to keep the platform running smoothly
        * Data processing and analysis
        * Market data updates
        * User data updates
        * Notification system
        * Agent communication and Memory management
        * etc.
      </Tab>

      <Tab title="Integrations">
        <CardGroup cols={4}>
          <Card title="Storage" icon="database">
            PostgreSQL
          </Card>

          <Card title="Document DB" icon="database">
            MongoDB
          </Card>

          <Card title="Vector Store" icon="network-wired">
            Qdrant
          </Card>

          <Card title="Graph Database" icon="database">
            Neo4j
          </Card>
        </CardGroup>
      </Tab>
    </Tabs>
  </Accordion>
</AccordionGroup>

## Scalability & Performance

With scale comes complexity. There are many moving parts, and we make sure that the platform is scalable and performant.

First of all, we scale the Nevrons swarm and the so-called "Agents Service" based on the load of background processes and real-time user requests.

<CardGroup cols={3}>
  <Card title="Load Distribution" icon="scale-balanced">
    Kubernetes workload balancing
  </Card>

  <Card title="Auto-scaling" icon="arrows-up-down">
    Kubernetes auto-scaling
  </Card>

  <Card title="Low Latency" icon="bolt">
    RPC streaming of processing results
  </Card>
</CardGroup>

## Additional Resources

<CardGroup cols={2}>
  <Card title="Nevron Documentation" icon="book" href="/technical/nevron/index">
    Learn more about the Nevron framework and how it empowers a swarm of 200+ AI Agents
  </Card>

  <Card title="Changelog" icon="road" href="/technical/neurodex/changelog">
    See what's new in the Neurodex
  </Card>
</CardGroup>

<Info>
  For technical support or architecture discussions, join our [developer community](https://t.me/Neurobro_Official).
</Info>