NextGen Agents Hackathon

Join us for a month-long hackathon where builders, dreamers, and innovators come together to create the next wave of smart applications.

August 1, 2025 to August 31, 2025

Online

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

Imagine AI agents tapping directly into decentralization. Your challenge is to fuse Internet Computer canisters with Fetch.ai uAgents on Agentverse, using ASI:One as your interface.

Deploy an Internet Computer canister smart contract to serve as your backend. Build a uAgent that interprets natural‑language prompts, makes HTTP calls to your canister, and turns the responses into chat replies using the ChatProtocol. Connect it all so anyone can chat with your agent and get instant responses.

Show us a focused use case in a domain of your choice that makes this integration meaningful. Register your uAgent on Agentverse, connect it to your Internet Computer backend, and demo live queries through ASI:One.

Dive into the docs from Fetch.ai and Internet Computer and start building.

Register here: https://dorahacks.io/hackathon/nextgen-agents/detail

What to Submit

Code
- Share the link to your public GitHub repository to allow judges to access and test your project.
- Ensure your README.md file includes key details about your agents, such as their name and address, for easy reference.
- Mention any extra resources required to run your project and provide links to those resources.
- All agents must be categorized under Innovation Lab.
  - To achieve this, include the following badge in your agent’s README.md file:
```
![tag:innovationlab](https://img.shields.io/badge/innovationlab-3D8BD3)
```
Video
- Include a demo video (3–5 minutes) demonstrating the agents you have built.
- Show interactions with your agent using either Chat with Agent or ASI:One.

Fetch.ai and ICP Integration Flow

Fetch.ai Tool Stack

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()

Fetch.ai Resources

How to create an Agent with uAgents Framework ↗Communication between two uAgents ↗Communication between two uAgents using Chat Protocol ↗Fetch.ai + ICP Integration Example ↗How to create ASI:One compatible uAgents ↗How to write a good Readme for your Agents ↗

ICP Resources

Hackathon Cheat Sheet ↗Internet Computer Developer Documentation ↗Internet Computer Capabilities ↗Awesome Internet Computer ↗Courses, Tutorials, and Samples ↗DeAI Playbook ↗Motoko ↗Rust ↗TypeScript ↗Python ↗

Video introduction

Introduction to agents

On Interval

On Event

Agent Messages

Examples to get you started:

Guide

How to Connect a Local Agent to Agentverse ↗

Guide

Fetch.ai + ICP Integration Example ↗

Guide

How to pass files to your uAgent ↗

Guide

MCP Integration Example ↗

Guide

Read our Medium Articles ↗

Judging Criteria

Uniqueness: Does the project introduce a novel Web3 use case leveraging Fetch.ai and ICP’s technology?
Revenue Model: Is there a clear plan for monetization and user adoption?
Full-Stack Development: Is the application functional end-to-end, achieving the desired functionality?
Presentation Quality: How well is the project described and presented (non-technical)?
Utility & Value: Does the project make sense, provide value, and address a real need?
Demo Video Quality: Does the demo clearly convey the idea, show the app’s flow, and walk through key code?
Code Quality: Is the code well-written, efficient, and maintainable?
Documentation: Is the project thoroughly documented, including:
- Introduction
- Architecture description
- Build and deployment instructions for local development
- Mainnet canister ID(s)
- ICP features used
- Fetch features used
- Challenges faced during the hackathon
- Future plans (if continuing post-hackathon)
Technical Difficulty: How challenging was the project to build, and were advanced features used (e.g., HTTP outcalls, timers, Bitcoin API, t-ECDSA, Chat Protocol in Fetch agents, etc.)?
Eligibility: Does the submission comply with team and participant criteria (2–5 members)?