Learn how to build and deploy intelligent agents right from your local machine.
In this session, I propose to walk-through how we can use open-source AI models such as Llama 3.2, or Phi 4, or DeepSeek-R1 to create their personalized AI agents. Be it an on-chain (web3) actions agent that performs transactions on blockchain, DeFi agent or a digital twin or a personal coding assistant, you can learn to do them all from this session.
I'll cover:
- How to download and setup required to create & deploy AI Agents
- Techniques & tools to convert knowledge bases from plain text file or markdown or PDF or CSV into an embedding
- Agents are used in real workflows or directly in real applications.
- Some tips and tricks to improve performance on local machines
- How to keep everything private to your machines and not let any external provider have access to your data
Remember if you're a windows user to install WSL before you attend this session.
Understanding the landscape of open-source AI models like Llama 3.2 and other SLMs too!
How and why open-source models matter and how they can help anyone adopt AI locally
Step-by-step guide to building and running AI agents locally
Practical applications and how to integrate AI agents into projects