MicMicrobial communities play a vital role in most processes in the biosphere and are essential for solving present and future environmental challenges. Examples include the impact of the human microbiome on health and disease, the discovery of new antibiotics, and turning waste products into valuables. In the past 10 years, new DNA sequencing-based methods have revolutionized our access to the genomes of microbial communities and have sparked an explosion of new fundamental discoveries based on genomic evidence. However, despite the fundamental discoveries enabled by new methods in the past decade, we are far from having a meaningful genomic representation of the tree of life - and we are even further away from understanding how microbes realize their genomic potential in complex environments. This is underlined by the fact that the current microbial genome databases contain genomic information on 47,894 prokaryotic species, while the most conservative analysis estimates millions of different species in nature. The NanoEat project will enable the next generation of large-scale studies in microbial communities to answer the fundamental questions of who is there and what do they eat. In nature, most microbes modify their DNA in highly specific combinations, either as a defense system against viruses or to regulate activity. In NanoEat we will exploit this feature using the raw Nanopore sequencing signal that, in principle, enables discovery of any type of modified DNA. By developing new machine learning frameworks that can identify these species-specific modification patterns we can utilize this novel feature to supercharge recovery of individual microbial genomes from complex communities. Furthermore, by supplying synthetic nucleotides, that can be detected by Nanopore sequencing, we hypothesize that it is possible to estimate how microbes grow, by using the incorporation rate of these synthetic nucleotides to estimate replication in complex communities at scale.