Traditional water quality monitoring involving sample collection and laboratory analysis is costly and time consuming, limiting possible responses to microorganisms that can damage the environment and human health. This project presents an open source, low cost, real time, in-situ microbial monitoring system that combines lensfree holographic imaging with autonomous sample collection. The system uses a 532 nm LED, a peristaltic pump, and a 64-megapixel camera to collect images that are then holographically reconstructed to a higher resolution. It is validated by creating object detection models that can differentiate between different types of cyanobacteria and by collecting open sourced datasets of cyanobacteria in water and filamentous bacteria in activated sludge. Additionally, the system demonstrates the potential to estimate total suspended solids (TSS) using image-based analysis. The system, with parts costing around $200, can detect microorganisms as small as 5 µm while maintaining a maximum throughput of 15.5 mm³. This work demonstrates the potential for large-scale, continuous monitoring of microbial populations in freshwater and wastewater environments, and can be widely deployable, particularly in resource limited settings. It also provides a foundation for future machine learning based analysis of lensfree holographic imaging
