# tensorflow/tensorflow

An Open Source Machine Learning Framework for Everyone

Repository: https://github.com/tensorflow/tensorflow
Canonical: https://ross.abutalabs.com/products/tensorflow
Homepage: https://tensorflow.org
Language: C++
License: Apache-2.0
License Family: permissive
Topics: tensorflow, machine-learning, python, deep-learning, deep-neural-networks, neural-network, ml, distributed
Last push: 2026-08-27T00:14:21+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 61, longevity 100
- inputs: {"age_days": 3953, "days_push": 7, "days_rel": 180, "gap_med": 68.5, "n_releases_24m": 7}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 197638, forks 76153 (observed 2026-08-28T04:12:28.427888+00:00)

## What it is
TensorFlow is an end-to-end open source platform for machine learning with stable Python and C++ APIs and a broad ecosystem of tools. It supports building, training, and deploying ML models across servers, edge devices, browsers, and mobile platforms.

## Use cases
- train deep neural networks for image classification
- build and deploy ML models in production
- run machine learning inference on mobile and edge devices
- run models in the browser with JavaScript
- distributed training on GPUs across machines
- build production ML pipelines with TFX
- train reinforcement learning agents
- graph neural network modeling

## When to choose
- you need a mature, production-proven ML framework with a large ecosystem
- you want to deploy models to mobile, edge, or web environments
- you need distributed training across heterogeneous hardware
- you want high-level Keras APIs plus low-level control

## When to avoid
- you prefer PyTorch's research-first ecosystem or need PyTorch-specific tooling
- you only need lightweight inference on microcontrollers where a smaller runtime suffices
- your team is already standardized on another framework

## Facets
- artifact type: framework
- maturity: stable
- function: machine-learning, deep-learning, llm-training, gpu-computing, data-science
- domain: machine-learning, deep-learning, artificial-intelligence, data-science, computer-vision
- platform: python, cpp, windows, browser, cross-platform
- tags: keras, neural-networks, distributed-training, tensorflow-lite, tensorflowjs, tfx, model-deployment, eager-execution, natural-language-processing, linux, macos, android, ios, gpu, docker

## Member repositories
- tensorflow/tensorflow (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:28.427888+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 2026-08-29T16:10:30.901736+00:00, confidence not recorded.
  - readme: https://github.com/tensorflow/tensorflow (fetched 2026-08-28T04:12:28.427888+00:00, sha 8387400e21d4)
  - homepage: https://tensorflow.org (fetched 2026-08-28T17:22:33.484052+00:00, sha ab510dcb6040)
  - site_page: https://www.tensorflow.org/install (fetched 2026-08-28T17:22:33.492510+00:00, sha 584a762da891)
  - site_page: https://www.tensorflow.org/tfx/api_docs (fetched 2026-08-28T17:22:33.496501+00:00, sha 6977825696fe)
  - site_page: https://www.tensorflow.org/about (fetched 2026-08-28T17:22:33.499865+00:00, sha 817250744d91)
  - site_page: https://www.tensorflow.org/about/case-studies (fetched 2026-08-28T17:22:33.501527+00:00, sha e6701029eec0)
  - site_page: https://www.tensorflow.org/about/bib (fetched 2026-08-28T17:22:33.505076+00:00, sha 5ca8943386b9)
  - site_page: https://www.tensorflow.org/community/contribute (fetched 2026-08-28T17:22:33.498208+00:00, sha 77d394fa76e7)
  - site_page: https://blog.tensorflow.org/2024/02/graph-neural-networks-in-tensorflow.html (fetched 2026-08-28T17:22:33.503372+00:00, sha fd6c6556fa89)
- Data as of 2026-08-30T08:39:29.467469+00:00.