Even in what has been termed an age of `precision cosmology’ certain anomalies on a range of astrophysical scales are observed and demand the existence of unseen types of matter or modifications to our current gravitational theory. In this article the issue of the nature of the mysterious `dark energy’ has been explored in a model-independent way. A maximum-entropy technique is developed and used to reconstruct the equation of state of dark energy within a bayesian framework. The motivation for the use of the MaxEnt technique is the lack of good data points in comparison to the number of parameters required for a sufficient characterization of dark energy. The method is shown to faithfully recover $w(z)$ from a hypothetical dataset in the presence of controlled error. Including the model into hypothesis space and marginalizing over it removes this dependence without a large cost to accuracy. Using the current WMAP3 measurement of the CMB shift parameter, the baryon acoustic oscillation (BAO) measurement the type 1 a supernovae (SNIa) from the HST/GOODS program and the first year Supernoave Legacy Survey, we derive constraints on the equation of state w(z) which are model-independent.