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.
A large-scale benchmark for co-optimizing the design and control of soft robots, as seen in NeurIPS 2021.
| Date | Stars |
|---|---|
| 2026-07-25 | 257 |
| 2026-07-28 | 257 |
| 2026-07-30 | 257 |
| 2026-08-06 | 257 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Evolution Gym
[](https://github.com/EvolutionGym/evogym/actions/workflows/wheels.yml)
[](https://github.com/EvolutionGym/evogym/actions/workflows/test.yml)
Evolution Gym is a large-scale benchmark for co-optimizing the design and control of soft robots. It provides a lightweight soft-body simulator wrapped with a gym-like interface for developing learning algorithms. EvoGym also includes a suite of 32 locomotion and manipulation tasks, detailed on our [website](https://evolutiongym.github.io/all-tasks). Task suite evaluations are described in our [NeurIPS 2021 paper](https://arxiv.org/pdf/2201.09863).
<br>
<p align="center">
<a href="https://forms.gle/Rn1TwzYGuVSAPQKfA" target="_blank" style="text-decoration: none;">
<img src="https://img.shields.io/badge/Get%20feature%20notifications-orange?style=for-the-badge&logo=tacobell&logoColor=black&color=fda158" alt="Get notified on releases">
</a>
<!-- -->
<a href="https://forms.gle/vH5Ta7HtVVQb6GpR9" target="_blank" style="text-decoration: none;">
<img src="https://img.shields.io/badge/Submit%20a%20feature%20request-blue?style=for-the-badge&logo=googleforms&logoColor=black&color=a3d7ff" alt="Submit a feature request">
</a>
</p>
<!-- <p align="center">
<a href="https://forms.gle/Rn1TwzYGuVSAPQKfA" target="_blank">
<img src="https://img.shields.io/badge/🔔%20Get%20feature%20notifications-orange?style=for-the-badge&logoColor=black&color=ff8119" alt="Get notified on releases">
</a>
<a href="https://forms.gle/vH5Ta7HtVVQb6GpR9" target="_blank">
<img src="https://img.shields.io/badge/Submit%20a%20feature%20request-blue?style=for-the-badge&logo=googleforms&logoColor=white&color=199cff" alt="Submit a feature request">
</a>
</p> -->
> [!NOTE]
> **[06/25]** 90k+ robot structures and 2.5k+ robot policies from the original EvoGym paper are now [available for download with instructions](https://github.com/EvolutionGym/evogym-datasets)!
> [!NOTE]
> **[07/24]** EvoGym has been recently updated! TLDR: requirements have been modernized (gym/gymnasium, numpy, etc.), and the library is now pip-installable.
[//]: # (<img src="https://github.com/EvolutionGym/evogym/raw/main/images/teaser-low-res.gif" alt="teaser" width="800"/>)
# Installation
EvoGym supports python `3.7` to `3.10` on most operating systems:
```shell
pip install evogym --upgrade
```
<!-- > [!CAUTION]
> This doesn't work yet -- coming soon! For now, you can install from test pypi:
> ```shell
> pip install "numpy<2.0.0" gymnasium
> pip install -i https://test.pypi.org/simple/ evogym
> ``` -->
On **Linux** install the following packages (or equivalent):
```shell
sudo apt-get install xorg-dev libglu1-mesa-dev
```
## From Source
If your platform is not supported, you may alternatively build from source:
### Requirements
* Python 3
* Linux, macOS, or Windows with [Visual Studios 2017](https://visualstudio.microsoft.com/vs/older-downloads/) build tools.
* [CMake](https://cmake.org/download/)
Clone the repo and submodules:
```shell
git clone --recurse-submodules https://github.com/EvolutionGym/evogym.git
```
On **Linux only**:
```shell
sudo apt-get install xorg-dev libglu1-mesa-dev
```
Finally, to install `evogym`, run the following in the environment of your choice:
```shell
pip install -e .
```
## Test Installation
If you have the repo cloned, `cd` to the `examples` folder and run the following script:
```shell
python gym_test.py
```
Alternatively, you can run the following snippet:
```python
import gymnasium as gym
import evogym.envs
from evogym import sample_robot
if __name__ == '__main__':
body, connections = sample_robot((5,5))
env = gym.make('Walker-v0', body=body, render_mExcerpt of 8,306 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a8f11c39820df9f2, topic:robotics, topic:simulation, readme:manipulation
matched fp:a8f11c39820df9f2, topic:reinforcement-learning, topic:deep-reinforcement-learning