Aiify.io {AI Agents} Love Hack

Build, connect, and communicate with AI Agents at the {AI Agents} Love Hack.

February 15, 2025

Digital Garage, Innovation Lab, San Francisco, CA

Schedule

Saturday, February 15

Time

Topic

Location

09:00 PST

Doors Open

Innovation Lab, San Francisco

10:00 PST

Opening Remarks, Logistics, & Sponsor Intros

Innovation Lab, San Francisco

11:00 PST

Team Building (pitch your project to find collaborators)

Innovation Lab, San Francisco

11:30 PST

Partner Workshops

Innovation Lab, San Francisco

13:00 PST

Lunch

Innovation Lab, San Francisco

14:00 PST

Hack Hack Hack!

Innovation Lab, San Francisco

Sunday, February 16

Time

Topic

Location

09:00 PST

Doors Reopen / Breakfast

Innovation Lab, San Francisco

14:00 PST

Project Submissions

Innovation Lab, San Francisco

14:00 PST

Lunch

Innovation Lab, San Francisco

15:00 PST

Preliminary Judging

Innovation Lab, San Francisco

17:00 PST

Finalist Presentations

Innovation Lab, San Francisco

18:30 PST

Celebration & Networking

Innovation Lab, San Francisco

20:00 PST

Doors Close

Innovation Lab, San Francisco

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

AI Agent Challenge

Unleash your creativity by designing specialised AI Agents in any domain—whether it's Finance, Healthcare, Education, or Social Impact using any Agentic framework of your choice, register your agents on Agentverse, a dynamic central directory where agents seamlessly interact and collaborate to deliver powerful solutions.

Take it a step further by building a personalized assistant that leverages the Search and Discovery feature on Agentverse. Your assistant will intelligently connect with other agents to fulfil user needs, orchestrating tasks with precision and efficiency.

Picture a world where users can effortlessly engage with a network of AI Agents tailored to their unique requirements—this is your opportunity to make it a reality.

Are you ready to innovate, collaborate, and automate the future of intelligent systems? The challenge awaits!

Qbio Challenge

This challenge focuses on developing a hybrid quantum-classical workflow to address a critical bottleneck in early-stage drug discovery: predicting the binding affinity of small molecule drug candidates to a target protein. Participants will leverage the strengths of both quantum and classical computing to achieve improved accuracy and efficiency compared to purely classical methods. The challenge emphasizes practical application on near-term (NISQ) quantum hardware while also encouraging consideration of future scalability.

Challenge Goal Develop a hybrid quantum-classical algorithm and workflow that accurately predicts the relative binding affinity of a small set of pre-selected drug-like molecules (ligands) to a specified protein target. The workflow should demonstrably leverage quantum computation for a specific, well-defined component of the binding affinity calculation, and integrate this seamlessly with classical methods for other necessary steps.

Additional Resources:

Complete verification through the #verification channel, wait for a few minutes and click here to join the ai-agents-love-hack channel on Discord to get access to the ligand and target data and connect with fellow innovators.

What to Build

In this hackathon, participants are encouraged to showcase their skills by building innovative solutions centered around AI Agents. Here's what you'll create:

Specialized AI Agents Use your creativity to design AI Agents tailored for specific domains or tasks, such as customer support, data analysis, content creation, research assistance, or more. Leverage agentic frameworks like uAgents, LangChain, CrewAI, Autogen, or others to build these agents. Once your agents are ready, register them on Agentverse using the Fetch.ai SDK enabling them to interact with other agents in the ecosystem. Your goal is to contribute to a diverse and robust agent directory.

Personalized Assistant Agent Build a Personalised Assistant Agent that uses the Search and Discovery feature on Agentverse. This assistant will dynamically connect with the most relevant agents-whether created by you or other participants to fulfil user queries and coordinate tasks efficiently. The assistant should intelligently manage interactions to deliver seamless, user-centric experiences.

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()