Interactive 3D math lessons with a live AI tutor

Explore algebra, calculus, and physics through visual scenes you can question, manipulate, and learn from.

See It in Action

Vision

AlgeBench transforms AI from an answer machine into a learning companion. It builds interactive mathematical worlds, performs the tedious work, and reveals the structures worth exploring, while preserving the joy of discovery for the learner. Always available, it serves as an infinitely patient tutor, helping users develop genuine understanding rather than simply consume answers.

Spin up a lesson, move the sliders, rotate the model, listen to the explanation, then interrupt with what, how, or why. The narrator answers in real time while the visualization stays connected to the math.

Who It's For

Students

Build intuition by manipulating equations, surfaces, vectors, and proofs instead of only memorizing formulas.

Educators

Create guided lessons that let students explore ideas at their own pace with narration, sliders, and visual checkpoints.

Self-Learners

Teach yourself with an AI tutor that can explain the current scene, answer follow-up questions, and adapt to your level.

Builders

Prototype mathematical scenes, lesson formats, and AI-assisted learning workflows on top of an open source stack.

What Makes AlgeBench Different

3D Scenes

Spin, zoom, and inspect mathematical objects in scenes that respond to your input

Live AI Narrator

Ask questions out loud while the tutor explains the scene and answers in context

Visual Proofs

Step through derivations with highlighted changes tied back to the visual model

Semantic Graphs

See variables, operators, and relationships as an interactive map of the equation

Scene Generation

Turn mathematical ideas into interactive lessons with narration, sliders, and visual structure

Open Source

Study the code, extend the lesson format, or adapt the project for your own courses

Run Locally

Run AlgeBench on your own machine in one of two ways. Either way you'll need a free Gemini API key.

Option 1 — Clone the repo

Requires Python 3.10+. The launcher sets up its virtual environment and installs dependencies on first run.

git clone https://github.com/ibenian/algebench
cd algebench
export GEMINI_API_KEY=your_key_here
./algebench

Then open localhost:8785 in your browser.

Option 2 — Docker image from Hugging Face

No clone, no Python setup — just Docker. Runs the prebuilt image from the Hugging Face Space registry.

docker run -it --pull=always -p 7860:7860 --platform=linux/amd64 \
  -e GEMINI_API_KEY="your_key_here" \
  registry.hf.space/ibenian-algebench:latest

Then open localhost:7860 in your browser. --pull=always fetches the newest build; --platform=linux/amd64 is needed on Apple Silicon and other ARM hosts.

Frequently Asked Questions

Follow the Demos

Watch walkthroughs, experiments, and new scene demos on the AlgeBench YouTube channel.

Try the hosted app instantly, or clone the repo to run it locally and contribute.