lmtp R package by Nick Williams implementing the methods we proposed here. Some features are:​​​

• Estimation of causal effects for static interventions and modified treatment policies in longitudinal data​

• Continuous, categorical, and binary exposures

• Incorporates Super Learner sl3 ensemble learners for flexible machine learning estimation of nuisance parameters

• Right-censored data

adjrct R package by Nick Williams implementing the methods we proposed here and in references therein. Some features are:​​​

• Estimation of covariate adjusted effects for randomized trials, with efficiency guarantees

• Estimation of effects for ordinal and time-to-event endpoints

• Incorporation of machine learning for maximum efficiency gains

medshift R package by Nima Hejazi:

• ​Incorporates Super Learner sl3 ensemble learners for flexible machine learning estimation of nuisance parameters

• Mediation analysis for stochastic interventions

• Continuous exposures

• Multivariate mediators

medoutcon R package by Nima Hejazi:

• ​Incorporates Super Learner sl3 ensemble learners for flexible machine learning estimation of nuisance parameters

• Mediation analysis for binary exposures in the presence of intermediate confounders

• Multivariate mediators