April 14, 2024
UCLA Pauley Pavillion, California
11:00 PDT
FetchAI Introduction workshop
Virtual Discord
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.
ASI-1 Mini - A Web3-native large language model (LLM) optimized for agent-based workflows.
Challenge statement
APIs, AI & ML Models, Databases and code is more often than not siloed. It works but only in the environment its defined to - which is a big problem! With Fetch.ai you can connect this siloed infrastructure to the world of agents and then make them universally accessible. By using AI Engine to chain these agents together you can create new data pipelines, businesses and AI driven opportunities. One agent might be serving predictions from a model from HuggingFace and this can be feeding an inference agent that is running on your local machine. We're introducing our Agent technology, the uAgent library and the Agentverse platform to enable you to create the software of the future, without being held back by legacy software design. What agents are you going to build? 🤔
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()
Examples to get you started:
Judging Criteria
WINNER TEAM
2ND TEAM
3RD TEAM
Judges
Edward FitzGerald
CTO
Humayun Sheikh
CEO
Attila Bagoly
AI head
Zoltan Mezei
AI Engineer
Sana Wajid
Programme Director
Elliot Bertram
Business Development
Mentors
Sanket Kulkarni
Ambassador
Natesh Reddy
Ambassador
Tanay Godse
Ambassador
Chinmay Nilesh
Ambassador