The future of agtech is open-source
The Project
What is the OpenWeedLocator (OWL)?
The OWL project started with an idea: what if farmers could build their own precision weed control technology?
After all, agriculture has always been an open-source industry. So we developed the OpenWeedLocator as an open-source, DIY, low-cost weed detector for green detection on fallow backgrounds designed to be practical, scalable, educational and accessible to all.
Using a credit card-sized Raspberry Pi computer, a camera, and 3D-printed parts, OWL gives farmers the tools to build solutions for their own specific needs. Besides the applied use cases, it’s a learning resource with an agricultural and practical twist for.
The Mission
Why Open-Source in Agriculture?
Agriculture has always been an open-source industry. Farmers shared ideas, discussed approaches over the fence and adjusted their tools to meet local conditions.
In the past, this ‘recipe sharing’ and adaptation could be done with drawings, welders, grinders and tools, but these days with the blackbox of technology, it is easy to end up with tools and agtech solutions that are locked away and unable to be adapted. The agtech field is full of incredible innovation, but too much of it is locked behind patents and proprietary systems.
An open-source approach, where we share code, hardware designs, and data, can transform our industry. It lowers the barrier to entry, allowing for faster development and more minds working on a problem. It means farmers aren't just consumers of technology; they are active participants in its creation.
The future of agtech shouldn’t depend on a few large companies. It should be a collaborative ecosystem where farmers can hack and adapt tools to meet the conditions, they know better than anyone. OWL is just one example of this philosophy in action.
The goal is to build a future where everyone has the tools to innovate.
The Vision
About the founder
I’m a researcher with a passion for agriculture, technology, and open-source development. I grew up with one foot in the city and the other on my dad's farm, which gave me an appreciation for the challenges and opportunities in agriculture. After starting down a path in medicine, I made the switch to ag science, which led me to a PhD at the University of Sydney focusing on machine learning and computer vision for weed recognition.
The OWL project grew out of my research and my belief that technology in agriculture shouldn't be a black box. I’m a strong proponent of open-source because I’ve seen how it can accelerate innovation in other tech industries, it helped me learn to code, and I believe agriculture is missing out if we don't adopt the same approach.