This paper presents a toolkit 1 for generating optimal policy projections. It makes five contributions. First, the toolkit requires a minimal set of inputs: only a baseline projection for target and instrument variables and impulse responses of those variables to policy shocks. Second, it solves optimal policy projections under commitment, limited-time commitment, and discretion. Third, it handles multiple policy instruments. Fourth, it handles multiple constraints on policy instruments such as a lower bound on the policy rate and an upper bound on asset purchases. Fifth, it allows alternative approaches to address the forward guidance puzzle. The toolkit that accompanies this paper is Dynare compatible, which facilitates its use. Examples replicate existing results in the optimal monetary policy literature and illustrate the usefulness of the toolkit for highlighting policy trade-offs. We use the toolkit to analyse US monetary policy at the height of the Great Financial Crisis. Given the Fed's early-2009 baseline macroeconomic projections, we find the Fed's planned use of the policy rate was close to optimal whereas a more aggressive QE program would have been beneficial.