BNB AI Hack

Artificial Super Intelligence (ASI) Challenge - Unlocking Agent Intelligence on BNB Chain

February 14, 2025

Virtual

Schedule

Friday, February 14

Time

Topic

Location

10:00 UTC

Hackathon Begins

Virtual

Tuesday, February 25

Time

Topic

Location

16:00 UTC

Workshop 1: Introduction to Fetch.ai and Agentverse

Tuesday, March 04

Time

Topic

Location

16:00 UTC

Workshop 2 : Power of AI Agents on Blockchain

Wednesday, May 14

Time

Topic

Location

10:00 UTC

Submission Period Starts

Virtual

Saturday, June 14

Time

Topic

Location

23:59 UTC

Submission Period Ends

Virtual

Monday, June 30

Time

Topic

Location

12:00 UTC

Top 10 Demos

Virtual

Monday, July 14

Time

Topic

Location

12:00 UTC

Winners Announcement

Virtual

Introduction

Fetch.ai’s vision is to create a marketplace of dynamic applications. We are empowering developers to build on our platform that can connect services and APIs without any domain knowledge.

Our infrastructure enables ‘search and discovery’ and ‘dynamic connectivity’. It offers an open, modular, UI agnostic, self-assembling of services.

Our technology is built on four key components:

uAgents - uAgents are autonomous AI agents built to connect seamlessly with networks and other agents. They can represent and interact with data, APIs, services, machine learning models, and individuals, enabling intelligent and dynamic decision-making in decentralized environments.

Agentverse - serves as a development and hosting platform for these agents.

Fetchai SDK – seamlessly integrates your AI Agent into Agentverse and empowers dynamic connectivity with the Fetch.ai SDK

Fetch Network - underpins the entire system, ensuring smooth operation and integration.

Challenge statement

Build an agent using Fetch agent tech that performs on-chain actions. Utilize Fetch.ai's cutting-edge agent technology to create an AI agent that autonomously performs on-chain actions. Your agent should effectively interact with smart contracts, execute transactions, and demonstrate intelligent use of blockchain capabilities.

Key Features to Showcase:

Agent Interaction: Enable the agent to autonomously communicate with other agents or external data sources.
On-Chain Execution: Design the agent to perform blockchain actions such as token transfers, contract calls, or governance voting
Smart Contract Integration: Create a scenario where the agent interacts with one or more smart contracts to accomplish a specific task.
Autonomy and Intelligence: Showcase decision-making capabilities using AI techniques (e.g., optimizing gas fees, and selecting the best trades).

Example Use Cases:

An agent that tracks token prices and executes trades based on predefined thresholds.
An agent that optimizes yield farming strategies by interacting with DeFi protocols.

Deliverables:

A fully functional Fetch.ai agent capable of performing at least one meaningful on-chain action.
Agents should be registered/hosted on Agentverse.
Comprehensive documentation explaining the agent’s design, setup, and functionality.
A short demo video demonstrating the agent in action.

Additional Information:

Please submit your projects on Devpost

Complete the authorisation process and join the bnb-ai-hack-sponsor-challenge channel on the BNB Chain Discord Server.

Fetch.ai tech stack

Product Overview

Quick start example

This file can be run on any platform supporting Python, with the necessary install permissions. This example shows two agents communicating with each other using the uAgent python library.
Read the guide for this code here ↗

from uagents import Agent, Bureau, Context, Model
    class Message(Model):
        message: str
    
    sigmar = Agent(name="sigmar", seed="sigmar recovery phrase")
    slaanesh = Agent(name="slaanesh", seed="slaanesh recovery phrase")
        
    @sigmar.on_interval(period=3.0)
    async def send_message(ctx: Context):
       await ctx.send(slaanesh.address, Message(message="hello there slaanesh"))
        
    @sigmar.on_message(model=Message)
    async def sigmar_message_handler(ctx: Context, sender: str, msg: Message):
        ctx.logger.info(f"Received message from {sender}: {msg.message}")
    
    @slaanesh.on_message(model=Message)
    async def slaanesh_message_handler(ctx: Context, sender: str, msg: Message):
        ctx.logger.info(f"Received message from {sender}: {msg.message}")
        await ctx.send(sigmar.address, Message(message="hello there sigmar"))
        
    bureau = Bureau()
    bureau.add(sigmar)
    bureau.add(slaanesh)
    if __name__ == "__main__":
        bureau.run()

Important links

How to create an Agent with uAgents Framework ↗How to create an Agent with Fetch.ai SDK ↗Communication between two uAgents ↗Communication between two Fetch.ai SDK Agents ↗How to write a good Readme for your Agents ↗Read our Medium Articles ↗

Video introduction

Introduction to agents

On Interval

On Event

Agent Messages

Examples to get you started:

Guide

AI Agents Reshaping the On-Chain Ecosystem ↗

Guide

Solana Agent Integration with Fetch.ai's uAgent ↗

Guide

How to Connect a Local Agent to Agentverse ↗

Guide

Build your Application using Fetch.ai SDK ↗

Guide

Integrating an Agent with Langchain ↗

Judging Criteria

Fetch.ai Tech Utilization – How well does the solution leverage the Fetch.ai agent framework, ensure interoperability with other agents, and integrate with Agentverse?
Technical Implementation – Is the code well-structured, efficient, and correctly handling on-chain interactions such as smart contract calls and transactions?
Agent Autonomy & Intelligence – How effectively does the agent make autonomous decisions, such as optimizing gas fees, executing trades, or participating in governance?
Impact & Use Case Viability– How relevant and useful is the agent in real-world blockchain applications such as DeFi, governance, or automation?