glmmTMB is an R package for fitting generalized linear mixed models (GLMMs) and extensions, built on Template Model Builder, which is in turn built on CppAD and Eigen. It is relatively new, but is intended to handle a wide range of statistical distributions (Gaussian, Poisson, binomial, negative binomial, Beta ...) as well as model extensions such as zero-inflation, heteroscedasticity, and autocorrelation. Fixed and random effects models can be specified for the conditional and zero-inflated components of the model, as well as fixed effects for the dispersion parameter.
glmmTMB is on CRAN, so you can install the latest release version in the usual way, i.e. install.packages("glmmTMB") .
You can install the very latest/development version of glmmTMB via
devtools::install_github("glmmTMB/glmmTMB/glmmTMB")
(this string denotes "Github user glmmTMB, repository glmmTMB, subdirectory glmmTMB"). If the install fails at the vignette-building step, try specifying build_vignettes=FALSE within the install_github call. Alternatively you can use install_github() from the ghit package, which has fewer dependencies. You'll need to have development tools (compilers etc.) installed first: devtools::setup_rtools() might help with that. Installing the source version will ensure that you get the very latest version of the package: since the package is in rapid development, that's a good idea.