Pakcoy is a type of vegetable that is very difficult to distinguish to determine the maturity level of the greenish color intensity for determination of harvest readiness in the Pakcoy plant. There needs to be a system reliable and smart to help farmers in the harvest process. On research This camera is used to take images of the Pakcoy plant. This research aims to test the accuracy of the detection object with two categories namely Pakcoy plants "Ready to Harvest" and "Not Ready to Harvest" using the Tensorflow Lite framework with the EfficientDet Lite 2 architectural model, Pakcoy plant detection was tested via an Android device and website online real time to assess the performance of the detection model. The test results show the average detection accuracy of Pakcoy Ready to Harvest vegetables touched the number 98.02% and 99.00% for detection of Pakcoy vegetables not ready for harvest, this indicates that the detection model is working reasonably well with the device android as well as website.