Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
An open-source Python framework for hybrid quantum-classical machine learning.
| Date | Stars |
|---|---|
| 2026-07-24 | 2172 |
| 2026-07-25 | 2172 |
| 2026-07-28 | 2172 |
| 2026-07-30 | 2172 |
| 2026-07-31 | 2175 |
| 2026-08-06 | 2175 |
| 2026-08-08 | 2175 |
| 2026-08-09 | 2176 |
| 2026-08-10 | 2177 |
| 2026-08-11 | 2177 |
| 2026-08-12 | 2178 |
| 2026-08-13 | 2177 |
| 2026-08-14 | 2178 |
| 2026-08-15 | 2179 |
| 2026-08-16 | 2179 |
| 2026-08-17 | 2180 |
| 2026-08-18 | 2180 |
| 2026-08-19 | 2181 |
| 2026-08-20 | 2180 |
| 2026-08-21 | 2179 |
| 2026-08-22 | 2179 |
| 2026-08-25 | 2179 |
| 2026-08-26 | 2180 |
| 2026-08-30 | 2179 |
| 2026-09-03 | 2179 |
| 2026-09-05 | 2179 |
| 2026-09-09 | 2181 |
| 2026-09-10 | 2181 |
| 2026-09-12 | 2183 |
| 2026-09-13 | 2182 |
| 2026-09-17 | 2181 |
| 2026-09-18 | 2182 |
| 2026-09-20 | 2183 |
Today
+1 stars today
This week
+1 stars this week
This month
+4 stars this month
Momentum
5.0
growth rate 0.05%/day
<!-- H1 title omitted because our logo acts as the title. -->
<div align="center">
<img width="450px" alt="TensorFlow Quantum logo"
src="https://raw.githubusercontent.com/tensorflow/quantum/refs/heads/master/docs/images/logo/tf_quantum1.svg">
High-performance Python framework for hybrid quantum-classical machine learning
[](https://github.com/tensorflow/quantum/blob/master/LICENSE)
[](https://www.python.org/downloads/)
[](https://pypi.org/project/tensorflow-quantum)
[Features](#features) –
[Installation](#installation) –
[Quick Start](#quick-start) –
[Getting help](#getting-help) –
[Citing TFQ](#citing-tensorflow-quantum) –
[Contact](#contact)
</div>
## Features
[TensorFlow Quantum](https://www.tensorflow.org/quantum) (TFQ) is a Python
framework for hybrid quantum-classical machine learning focused on modeling
quantum data. It provides users with the tools they need to interleave quantum
algorithms and logic designed in Cirq with the powerful and performant ML tools
from [TensorFlow](https://tensorflow.org). Here are some of TFQ's features:
* Integrates with [Cirq](https://github.com/quantumlib/Cirq) for writing
quantum circuit definitions
* Integrates with [qsim](https://github.com/quantumlib/qsim) for running
quantum circuit simulations
* Uses [Keras](https://keras.io) to provide high-level abstractions for
quantum machine learning constructs
* Provides an extensible system for automatic differentiation of quantum
circuits
* Offers many methods for computing gradients, including parameter shift and
adjoint methods
* Implements operations as C++ TensorFlow Ops, making them 1<sup>st</sup>-class
citizens in the TF compute graph
* Harnesses TensorFlow’s computational machinery to provide exceptional
performance and scalability
TensorFlow Quantum empowers quantum algorithms and machine learning researchers
to pursue questions whose answers can only be obtained through fast simulation
of many millions of moderately-sized circuits. It has already been instrumental
in enabling ground-breaking research in QML by providing a seamless workflow for
leveraging Google’s quantum computing offerings.
## Installation
Please see the [installation
instructions](https://www.tensorflow.org/quantum/install) in the documentation.
_Compatibility_: At this time, TensorFlow Quantum is built and
tested on Linux with the following systems and software:
* Python 3.10–3.12
* TensorFlow 2.19.1
* TF-Keras 2.19.0
* NumPy 2.0
* Cirq 1.5.0
## Quick start
[Guides and tutorials for TensorFlow
Quantum](https://tensorflow.org/quantum/overview) are available online at the
TensorFlow.org web site.
[Documentation for TensorFlow Quantum](https://tensorflow.org/quantum),
including tutorials and API documentation, can be found online at the
TensorFlow.org web site.
All of the examples can be found in GitHub in the form of [Python notebook
tutorials](https://github.com/tensorflow/quantum/tree/master/docs/tutorials)
## Getting help
Please report bugs or feature requests using the [TensorFlow Quantum issue
tracker](https://github.com/tensorflow/quantum/issues) on GitHub.
There is also a [Stack Overflow tag for TensorFlow
Quantum](https://stackoverflow.com/questions/tagged/tensorflow-quantum) that you
can use for more general TFQ-related discussions.
## Citing TensorFlow Quantum<a name="how-to-cite-tfq"></a><a name="how-to-cite"></a>
When publishing articles or otherwise writing about TensorFlow Quantum, please
cite Excerpt of 5,726 characters
Read on GitHub
312
Michael Hucka · Google · United States
208
Jae H. Yoo · Google · United States
168
87
24
Mark Daoust
13
Japan
8
Billy Lamberta
7
5
5
4
4
3
3
3
2
Balint Pato · Duke University
2
brett koonce · maps.loiter.ai
2
2
2
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:78c6be346d5f31fe, topic:tensorflow, readme:automatic differentiation