RxInfer.jl review
A focused Julia library for exact and variational inference on factor graphs.
Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026
RxInfer.jl is an open-source Julia package for specifying probabilistic models and performing Bayesian inference on factor graphs. It is aimed at researchers and developers working with probabilistic models, machine learning, signal processing, and dynamic systems. Its focused scope suits people who want to define models in Julia and work with inferred posterior distributions, rather than those seeking a general-purpose statistical analysis environment.
A central capability is generating message-passing algorithms automatically from a model's factor graph structure. RxInfer.jl supports exact belief propagation and variational message passing, as well as hybrid models with discrete and continuous latent variables. Results include posterior marginals and predictions, with optional Bethe Free Energy reporting. Users who need a particular model component can define custom factor nodes and message update rules. This makes the package relevant to specialized inference workflows, though users should expect to work directly with probabilistic models and inference concepts.
Inference can run on static datasets or asynchronous data streams, which gives the package a fit for both fixed observations and streaming workflows. It is installed through Julia's package manager, runs on Linux, macOS, and Windows, and lists Python as an integration. The MIT-licensed package is self-hosted, with documentation and community support channels. Choose RxInfer.jl if your work is centered on Bayesian inference in Julia and its message-passing approach; consider a broader statistics tool if you need general-purpose analysis beyond probabilistic models.
RxInfer.jl pros and cons
- Where it wins
- Generates message-passing algorithms from factor graph structure
- Supports exact belief propagation and variational message passing
- Runs inference on static datasets and asynchronous data streams
- Where it doesn't
- Focused on probabilistic inference rather than general statistics
- Requires working in Julia and expressing models in its syntax
- Customizing factor nodes and update rules calls for developer effort
RxInfer.jl fact sheet, pricing and score →
Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.
Last updated · How we research and update