Skip to content
Switch branches/tags
Go to file


Failed to load latest commit information.
Latest commit message
Commit time
Dec 16, 2019

Travis CI Status AppVeyor Status Docker Cloud Build Status Python Codecov Status Latest Release


Taichi (太极) is a programming language designed for high-performance computer graphics. It is deeply embedded in Python, and its just-in-time compiler offloads compute-intensive tasks to multi-core CPUs and massively parallel GPUs.

Advanced features of Taichi include spatially sparse computing and differentiable programming [examples].

Please check out our SIGGRAPH 2020 course on Taichi basics: YouTube, Bilibili, slides (pdf).

中文视频教程: [哔哩哔哩], [幻灯片]

Examples (More...)

Installation Downloads

python3 -m pip install taichi

Supported OS: Windows, Linux, Mac OS X; Python: 3.6/3.7/3.8 (64-bit only); Backends: x64 CPUs, CUDA, Apple Metal, OpenGL Compute Shaders.

Please build from source for other configurations (e.g., your CPU is ARM, or you want to try out our experimental C backend).


Linux (CUDA) OS X (10.14+) Windows Documentation
Build Build Status Build Status Build status Documentation Status
PyPI Build Status Build Status Build status


  • Taichi THREE: A 3D rendering library based on Taichi.
  • Taichi GLSL: A Taichi extension library that provides a set of GLSL-style helper functions.
  • Taichi Elements: A high-performance multi-material continuum physics engine based on Taichi (work in progress).
  • Taichi Blend: Taichi Blender intergration for physics-based animations (work in progress)
  • Taichi.js: Run compiled Taichi programs in Javascript and WASM (work in progress).


The Taichi project was created by Yuanming Hu (yuanming-hu). Significant contributions are made by:

Kenneth Lozes (KLozes) and Yu Fang (squarefk) have also made notable contributions.

[List of all contributors to Taichi]

The Simplified Chinese documentation (简体中文文档) was created by Ark (StephenArk30). Significant contributions are made by:

[List of all contributors to the Simplified Chinese documentation of Taichi]

We welcome feedback and comments. If you would like to contribute to Taichi, please check out our Contributor Guidelines.

If you use Taichi in your research, please cite our papers: