# pyro-ppl/pyro

Deep universal probabilistic programming with Python and PyTorch

Repository: https://github.com/pyro-ppl/pyro
Canonical: https://ross.abutalabs.com/products/pyro
Homepage: http://pyro.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: python, pytorch, machine-learning, bayesian, probabilistic-programming, bayesian-inference, variational-inference, probabilistic-modeling, deep-learning
Last push: 2026-08-04T04:33:37+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 96, release rhythm 8, longevity 100
- inputs: {"age_days": 3365, "days_push": 29, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9037, forks 1015 (observed 2026-08-28T04:10:28.053189+00:00)

## What it is
Pyro is a deep universal probabilistic programming library built on Python and PyTorch, supporting Bayesian modeling with variational inference, MCMC, and other scalable inference algorithms. It can represent any computable probability distribution and integrates with deep learning workflows.

## Use cases
- fit bayesian models with variational inference in python
- run MCMC sampling on a probabilistic model with PyTorch
- build a variational autoencoder with uncertainty estimates
- do bayesian hierarchical regression
- model time series with probabilistic forecasting
- estimate uncertainty in deep neural network predictions

## When to choose
- you want a flexible, universal PPL backed by PyTorch and GPU acceleration
- you need both automated and customizable inference (SVI, HMC/NUTS, SMC)
- you want to combine deep learning with Bayesian modeling
- you need to scale probabilistic models to large datasets

## When to avoid
- you want maximum HMC/NUTS speed and JIT compilation - consider NumPyro with JAX instead
- you need simple classical statistics without probabilistic programming
- your project is not Python/PyTorch based

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning, math, data-science
- domain: machine-learning, deep-learning, data-science
- platform: python, cross-platform
- tags: probabilistic-programming, bayesian-inference, variational-inference, mcmc, pytorch, generative-models, algorithms, gpu

## Member repositories
- pyro-ppl/pyro (main) score 66

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:28.053189+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:24:04.927790+00:00, confidence not recorded.
  - readme: https://github.com/pyro-ppl/pyro (fetched 2026-08-28T04:10:28.053189+00:00, sha 0c851d1ca9d0)
  - homepage: http://pyro.ai (fetched 2026-08-29T08:24:11.255089+00:00, sha 69f8af2b1a87)
  - site_page: http://docs.pyro.ai (fetched 2026-08-29T08:24:11.264273+00:00, sha ce164eea0777)
  - site_page: https://num.pyro.ai (fetched 2026-08-29T08:24:11.266162+00:00, sha 9c568f8cecd9)
- Data as of 2026-08-30T08:39:29.467469+00:00.