Large LLM models like ChatGPT and Claude are just a starting point for AI. Beyond them, thousands of developers are expanding their capabilities with integrations, workflows, and skills that further customize these models and how you interact with them.
Most of these projects are free and open source.If you've never come across the term open source before, it means that the code behind a project is publicly available for anyone to inspect, improve, and use. Rather than waiting for the big LLM players to ship the features you want, developers all over the world are experimenting in public and sharing what they create with the community.
Many of these projects live on GitHub. While GitHub has traditionally been a place for software developers, AI is changing that. Today, you don't need to know how to write code to benefit from the open-source ecosystem. A lot of these projects come with clear installation guides and AI can even walk you through the setup.
Learning how to discover and use these projects is becoming a valuable AI skill and it can be a big unlock for small frustrations around how your AI tools are working.
Before we start: if you are getting this email forwarded to you and are not yet part of the lab - you can join the tiny AI lab here.
The Challenge:
Find one open-source project that changes how you interact with your favourite LLM and install it.
Start by thinking about how you use your LLM tools today. Where do you find yourself repeating the same tasks? What feels clunky? What do you wish your AI could do better?
Then let your AI help you discover whether someone in the open-source community has already built a solution.
The prompt to get you started
Drop this into your AI of choice to get started:
I primarily use [ChatGPT / Claude / Gemini] for:
[Describe how you currently use it.]
Help me identify one limitation or frustration in my current workflow that could be improved with an open-source project.
Search GitHub and other reputable open-source repositories for projects that address this problem.
For each recommendation, explain:
What it does.
How it changes the way I interact with my LLM.
Who it's designed for.
Whether it's actively maintained.
How difficult it is to set up.
Any important security or privacy considerations.
Recommend the one you think will have the biggest impact on my workflow and explain why.
A few things to look for:
Open source is one of the most exciting parts of the AI ecosystem, but it's worth spending a few minutes evaluating a project before installing it.
As a general rule, look for projects that:
Have been updated recently.
Have clear documentation and installation instructions.
Have an active community of contributors and users.
If a project asks for access to your email, files, cloud storage, API keys, or other personal information, take a moment to understand why. If you're unsure, ask your AI assistant to explain what permissions the project needs and whether there are any potential security or privacy concerns before installing it.
Why this matters?
The AI models themselves are improving fast. But the open-source ecosystem around them is moving even faster, building solutions for specific problems the major labs will probably never touch.
The people who get the most out of AI over the next few years won't just be the ones with access to the newest model. They'll be the ones who know how to find, evaluate, and use what the open-source community is already building.
Learning to customize your AI puts you in the driver's seat and allows you to adjust the capabilities of your AI platform to support your specific needs.
That’s it for this week.
Hit reply and tell me what you thought of the challenge this week.
I read every response, and your experience helps me shape these challenges. If you get stuck or have questions, reach me at [email protected]