UC Berkeley AI Hackathon 2025 x Fetch.ai Innovation Lab
June 21, 2025 to June 22, 2025
ASUC Student Union: Martin Luther King Jr. Building
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
AI is no longer just about static models or passive automation—it's about building autonomous agents that can reason, adapt, and interact in real time. This hackathon challenges you to create intelligent agents that deliver real-world impact using the uAgents framework, Fetch.ai’s agentic LLM ASI:One, or any agentic framework of your choice.
Whether you're personalizing education, optimizing healthcare, enhancing sustainability, streamlining everyday tasks, or even just adding a bit of fun—your agents should work together to solve meaningful problems. From powerful tools to playful innovations, this is your chance to showcase the potential of agentic intelligence in action.
To get started: Register your agents on Agentverse—Fetch.ai’s open marketplace where agents can be discovered, coordinated, and made interoperable. Launch your agent and make it discoverable by ASI:One by implementing the Chat Protocol, which enables seamless natural language interaction with your agent.
Want to push the boundaries even further?
For enhanced capabilities, integrate Model Context Protocol (MCP) into your solution. This allows your agents to connect to external tools, APIs, and data sources, enabling more dynamic, real-world functionality.
This is your opportunity to code, collaborate, and help shape the future of AI—build agents that don’t just run, but think.
👉 Check out the resources to learn how to build and deploy your own AI agents.
-
Code
- Share the link to your public GitHub repository to allow judges to access and test your project.
- Ensure your
README.mdfile 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.mdfile:
-
-
Video
- Include a demo video (3–5 minutes) demonstrating the agents you have built.
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()
Examples to get you started:
Judging Criteria
-
Functionality & Technical Implementation (25%)
- Does the agent system work as intended?
- Are the agents properly communicating and reasoning in real time?
-
Use of Fetch.ai Technology (20%)
- Are agents registered on Agentverse?
- Is the Chat Protocol implemented for ASI:One discoverability?
-
Innovation & Creativity (20%)
- How original or creative is the solution?
- Is it solving a problem in a new or unconventional way?
-
Real-World Impact & Usefulness (20%)
- Does the solution solve a meaningful problem?
- How useful would this be to an end user?
-
User Experience & Presentation (15%)
- Is the solution presented clearly with a well-structured demo?
- Is there a smooth and intuitive user experience?
Prizes
Best Use of ASI:One
1500 USD
Cash Prize
Awarded to the team that demonstrates the most effective and creative implementation of Fetch.ai’s agentic LLM, ASI:One. Entries will be judged on problem selection, solution effectiveness, and potential real-world impact.
Best Deployment on Agentverse
750 USD
Cash Prize
Given to the team that makes the most impactful and well-presented launch on Agentverse, Fetch.ai’s open marketplace of AI agents. Judges will look for usability, discoverability, clarity of purpose, and potential for real-world adoption.
Best Interoperable Agent
750 USD
Cash Prize
Awarded to the team that builds the most cohesive and well-orchestrated multi-agent system. Judges will evaluate how effectively multiple agents communicate, collaborate, and coordinate tasks to solve a complex problem. The winning solution should demonstrate seamless agent-to-agent interactions.
Judges
Sana Wajid
Senior Vice President
Attila Bagoly
Chief AI Officer
Tanay Godse
AI Engineer
Chinmay Mahagaonkar
Junior Software Engineer
Mentors
Davel Radindra
Software Engineer
Sai Mounika Peteti
Ambassador
Schedule
10:00 PDT
Pre-Hackathon Workshop: Introduction to Fetch.ai
Google meet
13:00 PDT
How to Build AI Agents with the Fetch.ai Tech Stack
09:00 PDT
Hackers Check-in
10:00 PDT
Opening Ceremony Begins
11:00 PDT
Hacking Continues
11:00 PDT
Hacking Ends
13:00 PDT
Judging Begins
15:00 PDT
Judging Ends
15:30 PDT
Closing Ceremony Registration Begins
16:00 PDT
Closing Ceremony (Keynote, Pitches, Prizes)