This page shows some uses of Pymunk. If you also have done something using Pymunk please let me know and I can add it here!



My Sincerest Apologies

made by The Larry and Dan show (mauve, larry). Retrieved 2018-10-25

Winner of PyWeek 24 (Overall Team Entry)

A game of fun, shooting, and “I’m sorry to put you through this”.

A fabricator robot on Mars was supposed to make a bunch of robots! But it got lazy and made robots that could make other robots. And it made them smarter than they should have been. Now they’ve all gone off and hidden away behind various tanks and computers.

Happily, he knew how to construct you, a simple fighting robot. It’s your job to clean out each area!

See Daniel Popes teardown here for additional details


Beneath the Ice

made by Team Chimera (mit-mit, Lucid Design Ar). Retrieved 2016-09-25

Winner of PyWeek 22 (Overall Team Entry)

Beneath the Ice is a submarine exploration game and puzzle solving adventure! Uncover a mysterious pariah who can’t let you discover his secrets, who can’t let you in! Team Chimera take 3!



made by Tee. Retrieved 2016-01-25

Winner of PyWeek 20 (Overall Individual Entry)

A pachinko-like puzzle game. Play some balls and watch their movement carefully (i.e. collect data) to reconstruct the board!


Angry Birds in Python

made by Estevao Fonseca. Retrieved 2016-10-30

Angry Birds game written in python using pygame and pymunk



made by Paul Paterson. Retrieved 2016-01-25

A cave exploration game where you explore caves by descending into them on ropes.



Simulation of ambient chimes | Circle in a hexagon

made by Jan Abraham.Retrieved 2019-11-17

An ambient piano chord produced by the simulation of a bouncing ball. The calculations were carried out using pymunk library. Tuning: Kirnberger III


I teach AI to move with using NEAT

made by Cheesy AI. Retrieved 2019-11-17

Recently I learned Pymunk 2d physics library. It is very cool so with that I made 2d Humanoid for my AI. Today I’m going to teach AI to move forward with NEAT. NEAT is a genetic algorithm for the generation of evolving artificial neural networks. Results are quite weird but it will be fun. Have fun!


Car Configuration with Differential Evolotion

made by Nav. Retrieved 2019-05-05

Among the simplest AI algorithms: Differential Evolution. Brought to life with Pymunk and Pygame. Each car has an objective of reaching the end of the track, but has only 15 seconds to do so. They explore the multidimensional search space of vehicle speed, chassis width, chassis height and wheel radius, to find a variety of configurations among which few are successful in helping the car cross the track.



made by Jan Seidl. Retrieved 2018-06-13

VirtuaPlant is a Industrial Control Systems simulator which adds a “similar to real-world control logic” to the basic “read/write tags” feature of most PLC simulators. Paired with a game library and 2d physics engine, VirtuaPlant is able to present a GUI simulating the “world view” behind the control system allowing the user to have a vision of the would-be actions behind the control systems.


The Python Arcade Library

made by Paul. Retrieved 2018-03-05

Arcade is an easy-to-learn Python library for creating 2D video games. It is not directly tied to Pymunk, but includes a number of examples and helper classes to use Pymunk physics from a Arcade application.


billiARds A Game of Augmented Reality Pool

made by Alex Baikovitz. Retrieved 2017-05-21

Alex built billiARds for his 15-112 (Fundamentals of Programming and Computer Science) term project at Carnegie Mellon University. Made in Python3 using OpenCV, Pygame, and Pymunk. Users can simply use a pool cue stick and run the program on any ordinary surface.



made by Jay Shaffstall. Retrieved 2017-01-01

pyPhysicsSandbox is a simple wrapper around Pymunk that makes it easy to write code to explore 2D physics simulations. It’s intended for use in introductory programming classrooms.


Carrom Simulation

made by Samiran Roy. Retrieved 2016-10-27

An open source Carrom Simulator interface for testing intelligent/learning agents. It provides an interface that allows you to design agents that that play carrom. It is built in python, using pygame + pymunk. This is the course project for CS 747 - Foundations of Intelligent and Learning Agents, taught by Prof. Shivaram Kalyanakrishnan at IIT Bombay.


Self Driving Car

made by Matt Harvey. Retrieved 2016-08-07

A project that trains a virtual car to how to move an object around a screen (drive itself) without running into obstacles using a type of reinforcement learning called Q-Learning.

Papers / Science

Pymunk has been used or referenced in a number of scientific papers

  • Ipe, Navin. “An In-Memory Physics Environment as a World Model for Robot Motion Planning.” (2020).
  • Li, Yunzhu, Antonio Torralba, Animashree Anandkumar, Dieter Fox, and Animesh Garg. “Causal Discovery in Physical Systems from Videos.” arXiv preprint arXiv:2007.00631 (2020).
  • Suh, H. J., and Russ Tedrake. “The Surprising Effectiveness of Linear Models for Visual Foresight in Object Pile Manipulation.” arXiv preprint arXiv:2002.09093 (2020).
  • Vos, Bastiaan. “The Sailing Tug: A feasibility study on the application of Wind-Assisted towing of the Thialf.” (2019).
  • Wong, Eric C. “Example Based Hebbian Learning may be sufficient to support Human Intelligence.” bioRxiv (2019): 758375.
  • Manoury, Alexandre, and Cédric Buche. “Hierarchical Affordance Discovery using Intrinsic Motivation.” 2019.
  • Mounsif, Mehdi, Sebastien Lengagne, Benoit Thuilot, and Lounis Adouane. “Universal Notice Network: Transferable Knowledge Among Agents.” In 2019 6th International Conference on Control, Decision and Information Technologies (CoDIT), pp. 563-568. IEEE, 2019.
  • Du, Yilun, and Karthik Narasimhan. “Task-Agnostic Dynamics Priors for Deep Reinforcement Learning.” In International Conference on Machine Learning, pp. 1696-1705. 2019.
  • Siegel, Max Harmon. “Compositional simulation in perception and cognition.” PhD diss., Massachusetts Institute of Technology, 2018.
  • Caselles-Dupré, Hugo, Louis Annabi, Oksana Hagen, Michael Garcia-Ortiz, and David Filliat. “Flatland: a Lightweight First-Person 2-D Environment for Reinforcement Learning.” arXiv preprint arXiv:1809.00510 (2018).
  • Yingzhen, Li, and Stephan Mandt. “Disentangled Sequential Autoencoder.” In International Conference on Machine Learning, pp. 5656-5665. 2018.
  • Melnik, Andrew. “Sensorimotor Processing in the Human Brain and in Cognitive Architectures.” (2018).
  • Li, Yingzhen, and Stephan Mandt. “A Deep Generative Model for Disentangled Representations of Sequential Data.” arXiv preprint arXiv:1803.02991 (2018).
  • Hongsuk Yi, Eunsoo Park and Seungil Kim (이홍석, 박은수, and 김승일.) “Deep Reinforcement Learning for Autonomous Vehicle Driving” (“자율주행자동차 주행을 위한 심화강화학습.”) 2017 Korea Software Engineering Conference (한국정보과학회 학술발표논문집 (2017): 784-786.)
  • Fraccaro, Marco, Simon Kamronn, Ulrich Paquet, and Ole Winther. “A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning.” arXiv preprint arXiv:1710.05741 (2017).
  • Kister, Ulrike, Konstantin Klamka, Christian Tominski, and Raimund Dachselt. “GraSp: Combining Spatially‐aware Mobile Devices and a Display Wall for Graph Visualization and Interaction.” In Computer Graphics Forum, vol. 36, no. 3, pp. 503-514. 2017.
  • Kim, Neil H., Gloria Lee, Nicholas A. Sherer, K. Michael Martini, Nigel Goldenfeld, and Thomas E. Kuhlman. “Real-time transposable element activity in individual live cells.” Proceedings of the National Academy of Sciences 113, no. 26 (2016): 7278-7283.
  • Baheti, Ashutosh, and Arobinda Gupta. “Non-linear barrier coverage using mobile wireless sensors.” In Computers and Communications (ISCC), 2017 IEEE Symposium on, pp. 804-809. IEEE, 2017.
  • Espeso, David R., Esteban Martínez-García, Victor De Lorenzo, and Ángel Goñi-Moreno. “Physical forces shape group identity of swimming Pseudomonas putida cells.” Frontiers in Microbiology 7 (2016).
  • Goni-Moreno, Angel, and Martyn Amos. “DiSCUS: A Simulation Platform for Conjugation Computing.” In International Conference on Unconventional Computation and Natural Computation, pp. 181-191. Springer International Publishing, 2015.
  • Amos, Martyn, et al. “Bacterial computing with engineered populations.” Phil. Trans. R. Soc. A 373.2046 (2015): 20140218.
  • Crane, Beth, and Stephen Sherratt. “rUNSWift 2D Simulator; Behavioural Simulation Integrated with the rUNSWift Architecture.” UNSW School of Computer Science and Engineering (2013).
  • Miller, Chreston Allen. “Structural model discovery in temporal event data streams.” Diss. Virginia Polytechnic Institute and State University, 2013.
  • Pumar García, César. “Simulación de evolución dirigida de bacteriófagos en poblaciones de bacterias en 2D.” (2013).
  • Simoes, Manuel, and Caroline GL Cao. “Leonardo: a first step towards an interactive decision aid for port-placement in robotic surgery.” Systems, Man, and Cybernetics (SMC), 2013 IEEE International Conference on. IEEE, 2013.
  • Goni-Moreno, Angel, and Martyn Amos. “Discrete modelling of bacterial conjugation dynamics.” arXiv preprint arXiv:1211.1146 (2012).
  • Matthews, Elizabeth A. “ATLAS CHRONICLE: A STORY-DRIVEN SYSTEM TO CREATE STORY-DRIVEN MAPS.” Diss. Clemson University, 2012.
  • Matthews, Elizabeth, and Brian Malloy. “Procedural generation of story-driven maps.” Computer Games (CGAMES), 2011 16th International Conference on. IEEE, 2011.
  • Miller, Chreston, and Francis Quek. “Toward multimodal situated analysis.” Proceedings of the 13th international conference on multimodal interfaces. ACM, 2011.
  • Verdie, Yannick. “Surface gesture & object tracking on tabletop devices.” Diss. Virginia Polytechnic Institute and State University, 2010.
  • Agrawal, Vivek, and Ryan Kerwin. “Dynamic Robot Path Planning Among Crowds in Emergency Situations.”

List last updated 2020-07-09. If something is missing or wrong, please contact me!