BNB AI Hack

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

February 14, 2025

Virtual

Schedule

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 - Autonomous AI agents built to connect seamlessly with networks and other agents.
• Agentverse - A development and hosting platform for these agents.
• Fetchai SDK - Integrates your AI Agent into Agentverse.
• Fetch Network - Underpins the entire system.

Challenge statement

Leverage Fetch.ai's agent technology and the ASI-1 Mini Web3-native LLM to build an autonomous AI agent that performs on-chain actions efficiently. Your agent should interact with smart contracts and demonstrate AI-powered decision-making.

Key Features to Showcase

• Agent Interaction – Autonomous communication with other agents or external data sources.
• On-Chain Execution – Perform blockchain actions such as token transfers and governance voting.
• Smart Contract Integration – Interaction with one or more smart contracts.
• Autonomy & Intelligence – Decision-making capabilities to optimize processes.

Example Use Cases

• An agent tracking token prices for automated trading.
• An agent optimizing yield farming strategies via DeFi protocols.

Deliverables

• A fully functional Fetch.ai agent performing an on-chain action.
• Agents hosted on Agentverse.
• Comprehensive documentation detailing the agent’s design and functionality.
• A short demo video showcasing the agent in action.

Additional Information

• Hackathon Resources
• On-Chain Agent Integration
• ASI-1 Mini Integration Examples

Fetch.ai tech stack

Quick start example

This file can be run on any platform supporting Python.

Code Example

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()

Judging Criteria

• Fetch.ai Tech Utilization
• Technical Implementation
• Agent Autonomy & Intelligence
• Impact & Use Case Viability

Prizes

• Winner: $5000 USD
• Best Smart Contract Integration: $3000 USD
• The On-Chain Innovator Award: $2000 USD
• The Intelligent Automation Award: $2000 USD