The invention provides an abnormity detection method and system for developer behaviors in an open source community and a medium. The abnormity detection method comprises: a sequence construction step, i.e., constructing time sequences of different behavior times according to the developer behaviors; a behavior data discretization step, i.e., dividing the behavior frequency time sequence into different categories of which the differences in intervals are lower than a preset range and the differences between the intervals are higher than the preset range, and reaching a preset category number;a behavior frequent sequence mining step, i.e., performing behavior frequent sequence mining on the behavior sequences of other personnel and the historical behavior sequence of the to-be-detected person; and a behavior abnormality judgment step, i.e., judging whether the behavior of the developer is abnormal or not. According to the invention, the determinacy of the open source project is improved, and the project progress risk is reduced; and, according to the invention, historical data can be traced back, and past abnormal data can be identified.