tensorflow-probability
Probabilistic modeling and statistical inference in TensorFlow
Decision gist · record as of 2026-08-14
Yes, if you need probabilistic modeling or Bayesian inference in a TensorFlow workflow. The library is actively maintained, has low install friction, carries no security vulnerabilities, and offers a comprehensive toolkit for uncertainty quantification and statistical learning. Install with caution only if TensorFlow is not already a dependency in your project, since it adds a substantial indirect dependency; verify that the Beta status and potential interface changes align with your stability requirements.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires TensorFlow as an implicit dependency (not listed in runtime deps but essential for core functionality); also requires Python 3.9 or later.
- Low install friction with a pure-Python wheel and common dependencies.
- The package is actively maintained with recent commits and has been in development since 2018, though it carries a Beta development status indicating interfaces may still change.
License · maintenance · safety
Apache 2.0 (permissive) — Apache 2.0 is permissive, allowing commercial and private use with minimal restrictions—you must include a copy of the license and state significant changes, but there are no copyleft obligations.
last release 2024-11-08 (644 days) · last repo commit 2026-08-06 · 4,425 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 1,223,637 downloads/mo, #4,195 on PyPI
Alternatives
Verify before relying
pip install tensorflow-probability
import tensorflow_probability as tfp
dist = tfp.distributions.Normal(loc=0., scale=1.)
samples = dist.sample()- Whether TensorFlow is declared as a dependency elsewhere or must be installed separately by the user.
- Performance characteristics and scalability limits for large-scale probabilistic models on GPUs.
- Compatibility and feature parity between TensorFlow and JAX substrate implementations.
What it is and what it does
TensorFlow Probability is a library for probabilistic reasoning and statistical analysis built on top of TensorFlow. It provides a layered toolkit: distributions with broadcasting semantics, bijectors for transforming random variables, joint distributions for modeling dependencies, probabilistic neural network layers, and inference algorithms including MCMC, variational inference, and Monte Carlo methods. The library integrates automatic differentiation for gradient-based inference and supports hardware acceleration via GPUs and distributed computation.
It is designed for Bayesian machine learning workflows where you need to model uncertainty, perform hierarchical inference, or combine probabilistic methods with deep networks. The package also works as a JAX substrate, allowing the same probabilistic abstractions to run on JAX instead of TensorFlow. It is actively maintained but carries Beta status, meaning its public interfaces may change.
Use it for
- Build Bayesian neural networks with uncertainty over weights and predictions for safety-critical applications.
- Perform hierarchical statistical modeling and inference on grouped or nested data using joint distributions.
- Implement variational autoencoders and other deep generative models with probabilistic layers.
- Run MCMC sampling for posterior inference in complex probabilistic models.
- Estimate covariances, mixture models, and other statistical quantities with automatic differentiation.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you need probabilistic modeling or Bayesian inference in a TensorFlow workflow.
The library is actively maintained, has low install friction, carries no security vulnerabilities, and offers a comprehensive toolkit for uncertainty quantification and statistical learning. Install with caution only if TensorFlow is not already a dependency in your project, since it adds a substantial indirect dependency; verify that the Beta status and potential interface changes align with your stability requirements.
Install
tensorflow-probability on PyPI
Before you install
Low install friction with a pure-Python wheel and common dependencies. The package is actively maintained with recent commits and has been in development since 2018, though it carries a Beta development status indicating interfaces may still change.
Requires TensorFlow as an implicit dependency (not listed in runtime deps but essential for core functionality); also requires Python 3.9 or later.
License in practice
Apache 2.0 is permissive, allowing commercial and private use with minimal restrictions—you must include a copy of the license and state significant changes, but there are no copyleft obligations.
Quickstart
pip install tensorflow-probability
import tensorflow_probability as tfp
dist = tfp.distributions.Normal(loc=0., scale=1.)
samples = dist.sample()Verify before relying
- Whether TensorFlow is declared as a dependency elsewhere or must be installed separately by the user.
- Performance characteristics and scalability limits for large-scale probabilistic models on GPUs.
- Compatibility and feature parity between TensorFlow and JAX substrate implementations.
Package facts
| License | Apache 2.0 permissive |
| Python support | Supports the current Python release >=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 7 packagesabsl-pysixnumpydecoratorcloudpicklegastdm-tree |
| Maintenance | Actively maintained 644 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 1,223,637 / month, #4,195 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersIntended Audience :: EducationIntended Audience :: Science/ResearchLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.9Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial IntelligenceTopic :: Scientific/Engineering :: MathematicsTopic :: Software DevelopmentTopic :: Software Development :: LibrariesTopic :: Software Development :: Libraries :: Python Modules |
Evidence: tensorflow_probability-0.25.0-py2.py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “probabilistic modeling tensorflow”
- tensorflow-probabilityTensorFlow Probability provides probabilistic modeling, statistical…
- tfp-nightlyTensorFlow Probability provides probabilistic modeling, statistical…
- distraxDistrax provides JAX-native probability distributions and bijectors…
Give your agent the search over MCP, or paste the wish link into any chat.
More Software Development packages
Provides backported and experimental type hints for Python 3.9+, allowing use of newer typing features on older Python versions and enabling early experimentation with type system PEPs before they enter the standard library.
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
FastAPI is a Python web framework for building REST APIs using type hints, with automatic request validation, serialization, and interactive API documentation.
Provides a way to document function parameters, class attributes, return types, and variables inline using Python's `Annotated` type hint syntax instead of traditional docstrings.
Typer builds command-line applications from Python functions using type hints, automatically generating help text, argument parsing, and shell completion.
Install it if you are building CLIs in Python.
Distlib provides low-level packaging utilities for building, distributing, and managing Python software—including metadata handling, version specifiers, wheel support, script installation, and dependency resolution.
See also distrax · problog · pyjpt · tfp-nightly · pytensor-distributions · pyro-ppl · numpyro · emcee · pyro-api · ngboost