The traffic flows monitoring in a specific area is often an expansive and complicated activity for a public administration. Nevertheless, these data are fundamental for improving the urban and transport planning processes at local and regional levels. In the Italy-Croatia Interreg Mimosa project, an innovative opensource traffic flows monitoring system based on Artificial Intelligence (AI) was crated and tested. The collected results showed as the system is able to correctly recognize different typologies of vehicles (cars, bicycles, motorbikes, persons, light freight vehicles and heavy freights vehicles) using only open-source libraries. The aim is to provide to the decision makers new tools for the traffic monitoring and data-oriented decisions making on the topic of sustainable transport promotion. The Mimosa AI tool was published on GitHub and it is open access for all the interested public and private stakeholders. The paper presents the informatic architecture adopted, the key open-source AI tools used and it explores strengths and weaknesses related to the use of this AI tool.