Math animation tool. GPT-5.6 found and installed it itself to make a Fourier epicycle butterfly animation, which came out complex and better than GLM 5.2's.
Community-maintained Python library for programmatically creating mathematical and explanatory animations.
Updated EU status checked Last shown
Manim at a glance
- What is Manim?
- Manim is a library. Community-maintained Python library for programmatically creating mathematical and explanatory animations.
- Does Manim work in the EU?
- Available in the EU. Open-source MIT-licensed Python library installable locally anywhere via pip/uv or Docker, with no regional restrictions; the repo creation date is used as the release date. Last verified 14 Nov 2026.
- How much does Manim cost?
- Open source, open source. Free and open source under the MIT license. Licence: MIT.
- Where was Manim shown?
- In 2 creator videos by AI Search, Matthew Berman. Most recently by AI Search on 10 Jul 2026, at 12:33 in “GPT 5.6 is a BEAST”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
Manim is a Python animation engine for explanatory math videos. Users write scenes in code, describing objects such as LaTeX text, shapes, graphs and number planes, and the animations applied to them, and Manim renders the result to video. The Community Edition (ManimCE) is a fork of 3b1b/manim, the tool originally created by Grant Sanderson for the 3Blue1Brown videos, and is maintained by a community of contributors.
It supports LaTeX and MathTex rendering, transforms, function plots, vector fields and stream lines, boolean shape operations, and non-linear transformations of grids. Scenes are rendered from a command-line tool (for example manim -p -ql example.py SquareToCircle), and a %%manim IPython magic allows use in Jupyter notebooks. A Docker image and an online Jupyter environment are also provided.
Manim is free and released under the MIT license. It is a code library rather than a hosted service, so it is installed locally (documentation covers installation per operating system, and developers commonly use uv). According to the README, the project is undergoing a major refactor, and new feature contributions are generally not being accepted for now. YouTube creators have shown AI coding agents, including a Hermes skill and GPT models, using Manim to generate explanatory animations from prompts.
- Scene-based Python API for programmatic animations
- LaTeX and MathTex text rendering
- Graphs, number planes, vector fields and stream lines
- Command-line renderer with quality and preview flags
- Jupyter %%manim magic and Docker image
- MIT-licensed, community maintained
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Built-in Hermes skill that uses Manim to create explanatory motion-graphics videos. The creator generated a 58-second video explaining exponentials in a couple of minutes, using GPT 5.5.
Similar AI tools
Closest neighbours by meaning, not just by category.
SenseNova 6.8 Code2Video
Model · SenseTime
Open-weights 27B model from SenseTime that creates short videos by generating and rendering executable code.
VideoMDM
Research
Diffusion framework that learns text-to-3D human motion generation from 2D poses extracted from monocular videos.
HyperFrames
Library
Code-driven video rendering and motion-graphics library used with Claude to produce overlays, title cards and B-roll.
Millivid
Research
Research method for long-context video generation using hierarchical latents and coarse-to-fine rollout.
CogOmniControl
Research
Research framework for controllable video generation from sketches, pose or line art, a reference image and a text prompt.
Remotion
Library · Remotion
React framework for creating and rendering videos programmatically, with a Studio, Player and agent skills.