​Beginners Hands-On Workshop: Build Your First Simple AI Browser Agent Powered by Your Own Local Open-Source LLM

​Hello everyone!

​On Monday 8th December we're going to organise our last event for this year. We would like to extend a warm invitation to y'all. Tech in general & A.I. specifically is moving so fast, it's good to catch-up with all the new stuff (especially those A.I.-powered browsers like Comet or Atlas everyone's talkin' about ), that is before you go off-the-grid for a bit during this winter holiday season. This would be our 4th event in our series of local-first, open-source / open-weights AI systems.

​As usual, we would like to invite other like-minded people that are also into open-source / local A.I., people that want to go beyond your usual ChatGPTs and Anthropics and are not afraid of trying something that requires a bit of tinkering, but something that is a bit unpolished. That something could end-up helping you become more productive and gain more A.I. knowledge.

​We will be talking about AI Browser, what are they, in what situation you would use a particular AI Browser vs another or vs a Traditional Browser w/ or w/o extensions. We will be talking about the dangers of letting them do important tasks for you unsupervised and we will be talking about the dangers of leaking personal data when using poorly designed AI Browsers / Agents.

​This workshop is open to all levels, from beginners to experts.

​Bring your laptop (make sure it's fully charged if possible as local LLMs tend to be power-hungry), and, don't forget to bring your coding gear (whatever that might be, from keyboards to typing gloves). We will try to run A.I. models on the mobile phone as well so feel free to bring your phone fully charged with a little bit of free storage space.

​Prerequisite

​Ideally you should check the slides from the previous event to set up Ollama locally: https://andysign.github.io/ai-london-01/

​There is a second slide deck about how to run no-code agentic flows (you should know how to access it if you've been to the last workshop, if not join the Discord and ask us): https://andysign.github.io/ai-london-02/

​There is a third deck as well, about running RAGs locally with Anything LLM: https://andysign.github.io/ai-london-03/

​Agenda for the evening

​18:00 - 18:30: Arrival & Networking

Mingle with fellow developers over refreshments.

​18:30 - 18:45: Introductions (What is Local-First?)

Learn about self-hosted, local AI models and why we use them.

​18:45 - 19:30 Workshop

​Hands-on technical workshop (if you are non-technical it's OK, tag along).

​We'll explore a wide variety of AI-first browsers or AI-powered scrapers. The focus will be less on closed source ones and more on the open-source applications.

​If we're brave enough, will cover more advance things using some Python libraries for building your own AI system with browsing capabilities (you might be able to say "hey, AI, buy me a x-mass tree" and so relying on Silicon Valley).

​Prerequisite: a local Ollama / LMStudio (but if you don't have any of that, don't worry, come a bit early and we will help you).

​19:30 - 19:40 Fun and games (optional)

​Secret ;)

​19:40 - 20:15 Q&A

​Questions and answers or other announcements

​20:15 - 21:00 Networking

​Mingle with fellow tech enthusiasts over food and refreshments

​21:00 - Closing remarks and follow-up

​END: Carry on the fun at a nearby pub which is right around the corner.

​Event Venue

​We'd like to extend a heartfelt thank you to Encode Club.

​Encode Club has spent over five years fostering a global community of developers, researchers, and founders in Web3, AI, and emerging technologies. The Encode Hub brings everything together under one roof, providing a dedicated environment for collaboration and innovation through meetups, co-working, and in-person events.