integration-logo
DOCSEVENTS
BLOG
integration-logo
DOCSEVENTS
BLOG
Logo

Creating AI platforms and services that let anyone build and deploy AI services at scale, anytime and anywhere.

© 2025 Fetch.ai. All rights reserved.


EventsBlogCareersFetch.ai FoundationASI Wallet
Press and MediaPrivacy PolicyTerms of Service

Join our newsletter

hero-vector
hero-vector
hero-vector

We are proud to be the

Prime sponsor

of

AI Agent Hackathon 2.0 @ Paradox'25

Paradox'25 IITM

May 23, 2025

IIT Madras

Introduction

Fetch.ai’s vision is to create a open AI Agent marketplace. 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.

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

ASI:One - A Web3-native large language model (LLM) optimized for agent-based workflows.

Challenge statement

The AI agent landscape is evolving rapidly, yet many solutions remain either too generalized or overly technical for widespread adoption. Your mission is to build an innovative AI agent that leverages large language models—particularly the ASI:One LLM—and Fetch.ai's uAgents to effortlessly perform complex tasks specified through natural language instructions.

To demonstrate the practical power of AI Agents, create domain-specific solutions that solve real-world challenges through intuitive user interactions and tangible utility. For enhancing the capabilities of your agent, participants are encouraged to integrate the Model Context Protocol (MCPs) in their solution.

Are you ready to shape the next era of AI-driven automation? The challenge awaits!

👉 Check out the resources to learn how to build and deploy your own AI agents.

architecture

Tool Stack

architecture

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 ↗

code-icon
code-icon
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 ↗Communication between two uAgents ↗Communication between two uAgents using Chat Protocol ↗Read more about ASI:One ↗ASI:One API ↗How to write a good Readme for your Agents ↗
Video introduction
Video 1
Introduction to agents
Video 2
On Interval
Video 3
On Event
Video 4
Agent Messages

Examples to get you started:

Guide

How to Connect a Local Agent to Agentverse ↗

Guide

How to Integrate ASI:One LLM with your uAgent ↗

Guide

How to Create ASI:One compatible uAgents ↗

Guide

MCP Integration Example ↗

Guide

Read our Medium Articles ↗

Judging Criteria

Each row is scored 1 to 5, with a total score being your final score.
Parameters
Definition
Functionality
How well do your AI Agents perform their intended tasks? How effectively are APIs and frameworks integrated into your solution?
Agentverse Integration
Have you registered all your AI Agents on Agentverse?
Quantity of Agents Created
How many AI Agents have you created for this project? Does your submission demonstrate creativity and diversity in your AI Agents?
Personal Assistant Development
Does your assistant utilize the Search and Discover feature on Agentverse to dynamically connect with and coordinate tasks between multiple agents?
Innovation and Impact
Does your project address a real-world problem or introduce novel ideas?

Collaborators

partner-image
partner-image

Judges

Profile picture of Sana Wajid

Sana Wajid

Senior Vice President

Profile picture of Rishank Jhavar

Rishank Jhavar

Program Manager
(Developer Advocacy & Marketing)

Profile picture of Abhimanyu Gangani

Abhimanyu Gangani

Developer Advocate

Profile picture of Kshipra Dhame

Kshipra Dhame

Developer Advocate

Mentors

Profile picture of Dev Chauhan

Dev Chauhan

Developer Advocate

Profile picture of Geetanshi Goel

Geetanshi Goel

Ambassador

Profile picture of Gautam kumar

Gautam kumar

Developer Advocate

Schedule

Friday, May 23

Time

Topic

Location

06:00 IST

Build with Fetch: Pre-Hackathon Workshop & Walkthrough

Online

Tuesday, May 27

Time

Topic

Location

24:00 IST

Hacking and Submission Phase Start

Remote

Saturday, May 31

Time

Topic

Location

23:45 IST

Hacking and Submission Phase End

Friday, June 06

Time

Topic

Location

10:30 IST

Offline Mentoring Workshop

IIT Madras

Saturday, June 07

Time

Topic

Location

10:30 IST

Offline Presentation Round

IIT Madras