RxInfer.jl
rxinfer.com
- Free plan
- Linux
- API
7.4 Club score Visit rxinfer.com
Plans
Every plan and priceRxInfer.jl
Free
Free plan
What the maker publishes
- Bayesian analysis
- Yes source
- Deployment
- desktop source
- Extensibility
- The project describes support for custom operations and extensions with custom nodes and message update rules. source
- Free plan
- Yes source
- Inference methods
- It supports exact and variational inference algorithms. source
- Installation
- RxInfer is an officially registered Julia package installable with Julia's package manager. source
- Julia ecosystem
- RxInfer is built around ReactiveMP.jl for message passing, GraphPPL.jl for model and constraint specification, and Rocket.jl for reactive programming. source
- License
- RxInfer.jl is an MIT-licensed open-source project. source
- Limit
- The documentation notes that not all message-passing rules have analytical solutions; some cases may require numerical approximations or a different model structure. source
- Model features
- Its documented features include hybrid models with discrete and continuous latent variables, factorization constraints, graph visualization, and custom plugins. source
- Modeling
- It uses GraphPPL.jl to specify probabilistic models and inference constraints. source
- Purpose
- RxInfer.jl is a Julia package for Bayesian inference on factor graphs using reactive message passing. source
- Python access
- Documentation describes a REST API and Python SDK through RxInferServer.jl and RxInferClient.py, maintained by Lazy Dynamics as third-party projects that are not actively maintained by the core team. source
- Python integration
- A separate, third-party RxInferServer.jl REST API and RxInferClient.py SDK provide a way to use RxInfer from Python; the core team says these projects are unmaintained by it. source
- Reactive engine
- ReactiveMP.jl provides its message-passing inference engine, and Rocket.jl provides reactive extensions for Julia. source
- Scale
- The maker says it is designed to scale to models with millions of parameters and observations. source
- Scale and extensibility
- The documentation describes scalability to models with millions of parameters and observations, and support for custom nodes and message update rules. source
- Scripting support
- Yes source
- Session sharing
- Session sharing is optional; the docs say shared sessions contain metadata and errors, not actual data, and can be inspected locally. source
- Streaming
- Its inference API works with asynchronous infinite data streams as well as static datasets. source
- Streaming data
- The inference API works with asynchronous infinite data streams and static datasets. source
- Support
- The FAQ directs users to the documentation, GitHub Discussions, GitHub Issues, and regular community meetings for help. source
- Support
- The project points users to GitHub Discussions for community support and tracks bug reports through GitHub Issues. source
- Telemetry
- The package usage counter is enabled by default and records a timestamp, random UUID, and RxInfer and Julia versions; the docs say it collects no code or data and can be disabled. source
Checked against the maker's pages on 12 Oct 2026.