sbi is a Python package for simulation-based inference, designed to meet the needs of both researchers and practitioners. Whether you need fine-grained control or an easy-to-use interface, sbi has you covered.

A Python library for efficient Bayesian modeling with deep learning

A system for scientific simulation-based inference at scale.

Community-sourced list of papers and resources on neural simulation-based inference.

Likelihood-free AMortized Posterior Estimation with PyTorch

R package for statistical inference using partially observed Markov processes

Density estimation likelihood-free inference. No longer actively developed see https://github.com/mackelab/sbi instead

No description provided.

A Python toolkit for (simulation-based) inference and the mechanization of science.

Automatically convert Julia methods to Gen functions.

Simulation-based inference in JAX

Fast Bayesian optimization, quadrature, inference over arbitrary domain with GPU parallel acceleration

Julia package for simulation-based, likelihood-free parameter inference using neural networks.

Simulation-based (likelihood-free) inference customized for astronomical applications

SBI Workshop jointly by Helmholtz AI + ML ⇌ Science Colaboratory

Fast, lightweight and parallelised simulation-based inference in JAX.

Amortized Probabilistic Conditioning for Optimization, Simulation and Inference (Chang et al., AISTATS 2025)

ML4FP 2025: notebooks used for the Machine Learning for Fundamental Physics (ML4FP) School 2025

Normalizing flow models allowing for a conditioning context, implemented using Jax, Flax, and Distrax.

(NeurIPS 2022) Fast Bayesian Inference with Batch Bayesian Quadrature via Kernel Recombination

Probing the nature of dark matter by inferring the dark matter particle mass with machine learning and stellar streams.

A toolbox for the calibration and evaluation of simulation models.

A simulation-based Inference (SBI) library designed to perform analysis on a wide class of gravitational wave signals

Conduct simulation-based inference on strong gravitational lensing systems.

Evaluating model calibration methods for sensitivity analysis, uncertainty analysis, optimisation, and Bayesian inference

Code for the paper "Towards Reliable Simulation-Based Inference with Balanced Neural Ratio Estimation".

Hierarchical neural implicit inference over event ensembles. Code repository associated with https://arxiv.org/abs/2306.12584.

Example of a fully Bayesian forecast using evidence networks applied to 21-cm cosmology

Flexible SED fitting using Synthesizer, powered by Simulation Based Inference

Code for reproducing the experiments in the paper Neural Empirical Bayes: Source Distribution Estimation and its Applications to Simulation-Based Inference.