# blei-lab/edward

A probabilistic programming language in TensorFlow. Deep generative models, variational inference.

Repository: https://github.com/blei-lab/edward
Canonical: https://ross.abutalabs.com/products/edward
Homepage: http://edwardlib.org
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: bayesian-methods, deep-learning, machine-learning, data-science, tensorflow, neural-networks, statistics, probabilistic-programming
Last push: 2024-03-18T16:23:03+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3857, "days_push": 898, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4843, forks 741 (observed 2026-08-28T04:09:01.308258+00:00)

## What it is
Edward is a Python library for probabilistic modeling, inference, and criticism built on TensorFlow. It supports deep generative models, variational inference, and Monte Carlo methods for research in Bayesian statistics and machine learning.

## Use cases
- build bayesian neural networks in tensorflow
- run variational inference on probabilistic models
- fit deep generative models
- do hamiltonian monte carlo sampling
- posterior predictive checks for model criticism
- probabilistic programming for research

## When to choose
- you need a flexible testbed for probabilistic modeling research on TensorFlow
- you want variational inference or MCMC for deep probabilistic models

## When to avoid
- you need actively maintained tooling - Edward is largely superseded by TensorFlow Probability
- you work outside the TensorFlow 1.x ecosystem

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, simulation
- domain: machine-learning, deep-learning, data-science
- platform: python, cross-platform
- tags: probabilistic-programming, bayesian-inference, variational-inference, tensorflow, monte-carlo, generative-models, statistics, gpu

## Member repositories
- blei-lab/edward (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:01.308258+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 2026-08-29T18:18:27.247786+00:00, confidence not recorded.
  - readme: https://github.com/blei-lab/edward (fetched 2026-08-28T04:09:01.308258+00:00, sha a007c1016133)
  - homepage: http://edwardlib.org (fetched 2026-08-29T09:01:09.165234+00:00, sha 1f076f838138)
  - site_page: https://edwardlib.org/getting-started (fetched 2026-08-29T09:01:09.174452+00:00, sha 80013d7b7b78)
- Data as of 2026-08-30T08:39:29.467469+00:00.