​Learn how to use open-source harnesses like OpenCode & Pi w/ your own LLM and with it, build a real-world application

​Hello code campers!

​Since everyone is talking about using harnesses such as Anthropic Claude or OpenAI Codex, meaning, everyone is probably tired of hearing about them, we've decided to go in a different direction and explore other, less-known things such as, OpenCode and Pi DOT Dev.

​Figure 1: OpenCode VS Pi.Dev

​Come and join us and learn how to work with a wide range of open-source large language models (LLMs) such as DeepSeek V4, Gemma, Kimi K2, and GLM across various local-first environments. This comprehensive workshop designed to teach you what is a code harness, how many types of them there are out there (you might be familiar with Claude Code or Codex or CoPilot but there are others and since the big-tech companies are moving to token-based usage, why not run your own solution locally). We'll also explore how to go about having effective agentic coding workflows while benchmarking model performance and hardware requirements.

​We will go through the setup process, focusing on how to install the desired LLM runner like Ollama or LMstudio locally.

​This will be our 7th event in our series of local-first, open-source AI events; therefore, we will try to focus on building a setup that doesn't depend on Big Tech but on smaller open-source tech instead.

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

​Bring your laptop (make sure it's fully charged as local LLMs tend to be power-hungry), and don't forget to bring your coding gear (hoodie).

​We are delighted to announce that we are going to be accompanied by a guest speaker Vlad.

​BIO - Vlad S. is a software engineer with 20 years of experience delivering high-quality software for businesses, he developed a specific method for integrating local AI models into professional workflows, prioritizing code quality, efficiency, and control. In this 30-minute session, he will demonstrate a live coding workflow using local AI to produce production-grade code, showing how solo developers can adopt the technique and how it scales for larger organisations.

​Prerequisite

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

​If you want to take a quick look at the slides from the previous events fell free to do so:

​https://andysign.github.io/ai-london-01/ (Ollama);

​https://andysign.github.io/ai-london-02/ (LangFlow, not really related but still)

​https://andysign.github.io/ai-london-03/ (private RAG w/ Anything LLM)

​https://andysign.github.io/ai-london-04/ (AI-native browsers)

​https://andysign.github.io/ai-london-05/ (OpenClaw basics)

​https://andysign.github.io/ai-london-06/ (OpenClaw advanced)

​Agenda for the evening (Subject to change)

​18:00 - 18:30 Arrival and networking

Mingle with fellow developers over refreshments.

​18:30 - 18:45 Introductions

Intro and a bit of audience engagement

​18:45 - 19:40 Workshop

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

​20:30 - 20:45 Guest Speaker?

​20:30 - 21:00 Networking

​21:00 - Closing remarks and follow-up

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