Abstract Ecological models of community dynamics fall into two main categories. The neutral theory of biodiversity correctly predicts various large-scale ecosystem characteristics such as the species abundance distributions. On a smaller scale, the niche theory of species competition explains population dynamics and interactions between two to a dozen species. Despite the successes of the two theories, they rely on two contradictory assumptions. In the neutral theory each species is competitively equivalent while in the niche theory every species is specialized to exploit a specific part of its environment. Here we propose a resolution to this contradiction using a game theory model of competition with an attractor hyperplane as its equilibrium solution. When the population dynamics shifts within the hyperplane, it is selectively neutral. However, any movement perpendicular to the hyperplane is subject to restoring forces similar to what is predicted by the niche theory. We show that this model correctly reproduces empirical species abundance distributions and is also compatible with species removal experiments.