Unibase Docs
  • Introduction
    • Architecture
    • Core Components
    • Quick Start
  • Membase
    • 📚Architecture
    • Identity
    • Multi Memory
    • Authorization
    • 🚀Quick Start
  • AIP
    • Design
    • Agent Interaction Process
    • Implementation
    • Quick Start
      • Tool
      • Agent
        • Agent-Tool Interaction Via gRPC
        • Agent-Tool Interaction Via SSE
        • Agent-Agent Interaction
      • Chess game
  • Unibase DA
    • DA
    • Storage
    • Quick Start
      • Nodes boostrap
        • Storage Node
        • Validator Node
        • Stream Node
        • Docker
      • Nodes operations
  • Developers
    • Hub
    • SDK
    • API Reference
  • Alpha Testing
    • Testing plan
    • Requirements
    • Chains
  • 🚀Examples
Powered by GitBook
On this page
  1. Introduction

Architecture

PreviousIntroductionNextCore Components

Last updated 7 days ago

This layered architecture reflects the modular and decentralized nature of the Unibase ecosystem, where each layer builds upon the previous one to create a secure, scalable, and interoperable framework for AI agents.

1. Application Layer

The top layer, the Application Layer, consists of AI agents that are directly interacted with by users. This includes:

  • Various AI agents such as the Trader Agent, Personal Agent and Chess Agent. These agents can engage in tasks like trading, personal assistance and chess game.

2. Middleware

The Middleware layer serves as a bridge between the Application Layer and Core Layer. It contains:

  • Config Hub: Configuration management that allows for the customization of agent/tool behavior and interactions.

  • Memory Hub: Manages the persistent memory of agents, ensuring that they retain data and context across interactions.

  • Knowledge Base: A repository of shared knowledge, enabling agents to access and contribute to a decentralized, collective intelligence.

3. Core Layer

The Core Layer encompasses the essential building blocks that govern agent behavior, data exchange, and system interoperability:

  • AIP (Agent Interoperability Protocol): Defines the communication standards and interaction protocols between agents.

  • Membase: A decentralized memory and identity layer providing persistent storage for agent data and interactions.

  • DA: A decentralized storage system that ensures the availability and integrity of data on the blockchain.

4. Infrastructure

The Infrastructure Layer underpins the entire system, providing the foundational technologies that enable everything to function:

  • Blockchain: The decentralized ledger that secures transactions and agent identity verification.

  • Storage: Distributed storage solutions that securely store data and models, enabling scalable and efficient retrieval.

  • LLM API: The API enabling integration with large language models, offering advanced AI capabilities to the system.