I have not used any of these implementations, but have read several discussions on how some implementations do not always give the same answers as others, (namely matlab and R). My advice when looking at software you are unfamiliar with is that it would probably be best to try multiple implementations to make sure the results are compatible across programs. No one wants their research compromised by a software bug. That being said, there are some implementations I am aware of.

There is currently active development for a random forrest implementation in STATA, but I don't think it is complete yet.

There is an implementation of random forrest in SAS (enterprise miner)

http://analytics-in-writing.blogspot.com/2012/12/random-forest-modeling-in-sas-several.html

There are multiple implemetaions in matlab one called tree bagger, and another random forrest, (google "random forrest matlab")

Finally, if you can program, there is a random forrest toolkit with python bindings:

https://github.com/david-matheson/rftk

and another python implementation from scikit:

http://scikit-learn.org/stable/modules/ensemble.html

Some other implementations:

Charon (in F#) http://mathias-brandewinder.github.io/Charon/

DecisionTree (in Julia) https://github.com/bensadeghi/DecisionTree.jl

the STATISTICA software can be used to run the many of machine learning algorithm like Random forest, support vector machine, classification and regression tree, boosted regression tree, neural network and etc.

 Thanks a lot