Conservation teams collect more data than they can ever look at: years of audio, millions of camera-trap photos, endless hours of underwater video. The bottleneck isn’t passion or knowledge — it’s tooling. We’re a small team of engineers and ecologists who close that gap, building machine learning tools side by side with the researchers and rangers who use them.
Free to use. Free to modify. Open source, end to end.
What We Do
We take conservation research into production — covering the full lifecycle from raw field data to systems running in the field.
Data pipelines
Terabytes of audio, video, and sensor data turned into usable signals.
Custom ML models
Species ID, behavior detection, environmental monitoring — trained on your data.
Apps & deployment
Web apps and dashboards your team actually uses, running on anything from edge devices to the cloud.
Open source by default
Transparent, reproducible, and yours to keep — no vendor lock-in.
The Team
Arthur Caillau
Building open-source AI tools that empower conservationists worldwide. Passionate about making cutting-edge technology accessible to protect biodiversity and drive real-world conservation impact.
Jeremy Vuillermet
Crafting intuitive interfaces that put powerful conservation technology into the hands of field researchers and wildlife experts. Focused on creating seamless user experiences for complex AI-driven tools.
Eelke Folmer
Bridging ecology and technology through data science, geospatial analytics, and machine learning. Leverages drone imagery and photogrammetry to deliver actionable insights for conservation projects worldwide.
Thor Veen
Evolutionary biologist turned conservation technologist. Combines expertise in biodiversity monitoring with cutting-edge computer vision and machine learning to develop innovative wildlife tracking solutions.
The Journey
2024 — First field deployments
EarthToolsMaker starts shipping: coral reef health monitoring, forest elephant acoustics with Cornell, bear identification, and SalmonVision counting fish on British Columbia rivers.
2025 — Tools others can run
BioWatch turns camera-trap archives into maps and insights. Seal surveys take off over the Wadden Sea. Snow leopard monitoring begins in the mountains of Central Asia.
2026 — Earlier, faster, further
Sonar counts smolt runs no camera could see. Fire detection spots smoke at 35 km, minutes after ignition.
Help us keep these tools in the field
Your support sustains our ongoing projects — keeping tools maintained, models improving, and everything free for the people who rely on them.
Support our workOur Partners
View all
Work in the Field
Seeing smoke 35 km away
Early wildfire detection from tower-mounted cameras across European forests. With Pyronear.
Counting every salmon, every river
SalmonVision counts and classifies migrating salmon in real time from underwater cameras and sonar. With the Pacific Salmon Foundation.
Hearing elephants through the noise
Years of Congo-basin rainforest audio, scanned automatically for elephant rumbles — and gunshots. With Cornell's Elephant Listening Project.
Knowing one bear from another
Facial recognition for grizzlies — population monitoring without tags or tranquilizers. With the BearID Project.
Explore all 13 projects on our projects page — or grab the open-source tools behind them.
Have a conservation challenge?
Tell us about your data and your field problem — we'll give you an honest read on what's possible and what it would take.
Start a project