We are proud to be the
Anchor sponsor
CalHacks 12.0
October 24, 2025 to October 26, 2025
Palace of Fine Arts, San Francisco
Prizes
Best Use of Fetch.ai
$2500
Cash Prize + Internship Interview Opportunity
To qualify, teams must register their agents on Agentverse, enable the chat protocol, and integrate Anthropic's Claude (or any LLM) as the reasoning engine powering their agents. Judges will look for well-designed innovative agents that solve real problems, take meaningful actions, deliver exceptional user experience, and demonstrate strong implementation of the Fetch.ai ecosystem.
Best Deployment of Agentverse
$1500
Cash Prize + Internship Interview Opportunity
Given to the team that publishes the highest number of useful, discoverable, and well-documented agents on Agentverse. Judges will value scale, clarity, and how easy it is for others to find and use these agents.
Most Viral ASI:One Personal AI
$1000
Cash Prize + Internship Interview Opportunity
Awarded to the team whose ASI:One Personal AIs steals the spotlight on socials. Fine-tune your Personal AI, give it attitude, wit, and charm -- then share it on your socials - X, TikTok, or anywhere people can’t stop talking about it. Judges are looking for originality, humor, social engagement, and how well your AI interacts with others on Agentverse or with your own agents. If your AI has humor, chaos energy, and internet presence, you’re winning this.
Fetch.ai is your gateway to the agentic economy. It provides a full ecosystem for building, deploying, and discovering AI Agents. With Fetch.ai, you can:
- Build agents using the uAgents framework.
- Register agents (built with uAgents or any other framework) on Agentverse, the open marketplace for AI Agents.
- Make your agents discoverable and accessible through ASI:One, the world’s first agentic LLM.
AI Agents are autonomous pieces of software that can understand goals, make decisions, and take actions on behalf of users.
The Three Pillars of the Fetch.ai Ecosystem
- uAgents – A Python library developed by Fetch.ai for building autonomous agents. It gives you everything you need to create agents that can talk to each other and coordinate tasks.
- Agentverse - The open marketplace for AI Agents. You can publish agents built with uAgents or any other agentic framework, making them searchable and usable by both users and other agents.
- ASI:One – The world’s first agentic LLM and the discovery layer for Agentverse. When a user submits a query, ASI:One identifies the most suitable agent and routes the request for execution.
Challenge statement
🎯 Goal: Build and launch AI Agents on Agentverse that understand user goals & intent and take action to achieve them.
🤖 What are AI Agents? They are autonomous pieces of software that can understand goals, make decisions, and take actions on behalf of users.
🚀 Your Mission: Build agents that do, not just chat:
- Build with Fetch.ai Stack Agent Development: Use popular agentic frameworks like LangGraph, CrewAI, OpenAI Swarm, Google Agent Development Kit, etc., or build your agent from scratch in Python
Deployment & Discovery:
- Register agents on Agentverse using the uAgents library
- Implement the Chat Protocol for direct user interaction
- Make your agents discoverable through ASI:One
- Build custom applications that use agents in the backend
- Create seamless user experiences that hide complexity
LLM Integration: Power your agents with Anthropic's Claude (or Gemini’s multimodal capabilities, OpenAI, Groq inference, etc.)
- Design Intelligent Agents
- Take open-ended natural language goals and break them into actionable plans
- Use Claude's extended context (200K tokens), advanced reasoning, and tool use capabilities, Google Gemini’s multimodal capabilities, Groq’s fast inference, etc
- Adapt in real-time based on feedback and outcomes
- Enable Real-World Actions
- Level up with MCPs: Integrate Model Context Protocol to let your agents read/write files, call APIs, execute code, and access tools
- Go beyond conversation—make agents that actually complete tasks using any external APIs and Data
🌍 Inspiration
- Productivity & Automation – Agents that execute workflows like email management, CRM updates, document processing, social media scheduling, or project coordination.
- Finance & Business – Tools for expense tracking, invoice processing, investment analysis, portfolio optimization, or financial planning that help users save, invest, or manage money.
- Healthcare & Wellness – Appointment coordination, medication management, symptom tracking, health data analysis, or mental wellness support agents.
- Education & Research – Personalized tutors, research assistants, code reviewers, study planners, or language coaches that help people learn and understand complex topics.
- Creative & Content – Content generation pipelines, design assistants, video editing automation, or marketing campaign managers that create and distribute creative work.
- Multimodal Applications – Agents that process images, audio, video, or documents: receipt scanners, visual analyzers, transcription services, or document intelligence tools.
- DevOps & Infrastructure – Log analyzers, code review bots, deployment managers, or documentation generators for system monitoring and automation.
- Wildcard – Legal document processors, supply chain optimizers, customer support automation, travel planners, real estate analyzers—anything that uses the Fetch.ai stack and delivers real value.
📚 Resources 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.
Try it out on Agentverse ↗
from datetime import datetime
from uuid import uuid4
from uagents.setup import fund_agent_if_low
from uagents_core.contrib.protocols.chat import (
ChatAcknowledgement,
ChatMessage,
EndSessionContent,
StartSessionContent,
TextContent,
chat_protocol_spec,
)
agent = Agent()
# Initialize the chat protocol with the standard chat spec
chat_proto = Protocol(spec=chat_protocol_spec)
# Utility function to wrap plain text into a ChatMessage
def create_text_chat(text: str, end_session: bool = False) -> ChatMessage:
content = [TextContent(type="text", text=text)]
return ChatMessage(
timestamp=datetime.utcnow(),
msg_id=uuid4(),
content=content,
)
# Handle incoming chat messages
@chat_proto.on_message(ChatMessage)
async def handle_message(ctx: Context, sender: str, msg: ChatMessage):
ctx.logger.info(f"Received message from {sender}")
# Always send back an acknowledgement when a message is received
await ctx.send(sender, ChatAcknowledgement(timestamp=datetime.utcnow(), acknowledged_msg_id=msg.msg_id))
# Process each content item inside the chat message
for item in msg.content:
# Marks the start of a chat session
if isinstance(item, StartSessionContent):
ctx.logger.info(f"Session started with {sender}")
# Handles plain text messages (from another agent or ASI:One)
elif isinstance(item, TextContent):
ctx.logger.info(f"Text message from {sender}: {item.text}")
#Add your logic
# Example: respond with a message describing the result of a completed task
response_message = create_text_chat("Hello from Agent")
await ctx.send(sender, response_message)
# Marks the end of a chat session
elif isinstance(item, EndSessionContent):
ctx.logger.info(f"Session ended with {sender}")
# Catches anything unexpected
else:
ctx.logger.info(f"Received unexpected content type from {sender}")
# Handle acknowledgements for messages this agent has sent out
@chat_proto.on_message(ChatAcknowledgement)
async def handle_acknowledgement(ctx: Context, sender: str, msg: ChatAcknowledgement):
ctx.logger.info(f"Received acknowledgement from {sender} for message {msg.acknowledged_msg_id}")
# Include the chat protocol and publish the manifest to Agentverse
agent.include(chat_proto, publish_manifest=True)
if __name__ == "__main__":
agent.run()
Important links
Fetch.ai Resources
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 Fetch.ai
$2500
Cash Prize + Internship Interview Opportunity
To qualify, teams must register their agents on Agentverse, enable the chat protocol, and integrate Anthropic's Claude (or any LLM) as the reasoning engine powering their agents. Judges will look for well-designed innovative agents that solve real problems, take meaningful actions, deliver exceptional user experience, and demonstrate strong implementation of the Fetch.ai ecosystem.
Best Deployment of Agentverse
$1500
Cash Prize + Internship Interview Opportunity
Given to the team that publishes the highest number of useful, discoverable, and well-documented agents on Agentverse. Judges will value scale, clarity, and how easy it is for others to find and use these agents.
Most Viral ASI:One Personal AI
$1000
Cash Prize + Internship Interview Opportunity
Awarded to the team whose ASI:One Personal AIs steals the spotlight on socials. Fine-tune your Personal AI, give it attitude, wit, and charm -- then share it on your socials - X, TikTok, or anywhere people can’t stop talking about it. Judges are looking for originality, humor, social engagement, and how well your AI interacts with others on Agentverse or with your own agents. If your AI has humor, chaos energy, and internet presence, you’re winning this.
Judges
Sana Wajid
Chief Development Officer - Fetch.ai
Senior Vice President - Innovation Lab
Attila Bagoly
Chief AI Officer
Mentors
Abhi Gangani
Developer Advocate
Kshipra Dhame
Developer Advocate
Mike Chrabaszcz
Developer Advocate
Chayan Shah
Junior Software Engineer
Ryan Tran
Junior Software Engineer
Martin Ceballos
Junior Software Engineer
Thang Nguyen
Junior Software Engineer
Trung Tran
Junior Software Engineer
Schedule
19:00 PDT
Pre-Hackathon Workshop
Wheeler 204
16:00 PDT
Opening Ceremony Begins
Palace of Fine Arts
20:00 PDT
Fetch.ai Workshop
Palace of Fine Arts
20:00 PDT
Hacking Begins
Palace of Fine Arts
09:00 PDT
Hacking Continues (Rest of the day)
Palace of Fine Arts
13:00 PDT
Networking Session
Breakout 4
16:00 PDT
Coffee Chats
Breakout 1
10:30 PDT
Hacking Ends; Judging Begins
Palace of Fine Arts
13:00 PDT
Closing Ceremony
Palace of Fine Arts
17:00 PDT
CalHacks Ends
Palace of Fine Arts