Open-source · Free forever

See How AI Thinks
& Quantum Computes

Interactive, step-by-step dissection of deep learning, generative AI, and quantum algorithms. Watch every computation unfold — from binary search to self-attention.

Classical
7 algos
Deep Learning
5 algos
Generative AI
5 algos
Quantum
5 algos
Explore AlgorithmsView on GitHub

No account required · MIT Licensed · Python & JavaScript

eigenvue — Grover's SearchQuantum
Quantum Circuit — 3 Qubits
q₀
H
X
H
M
q₁
H
X
H
M
q₂
X
O
X
M
2

Apply Oracle: The oracle flips the phase of the target state |101⟩, marking it for amplification.

Step 2 / 5
22+
Interactive Visualizations
4
Algorithm Domains
MIT
Open Source License
pip + npm
Install Anywhere

How It Works

1

Pick an Algorithm

Choose from 22+ algorithms across classical CS, deep learning, generative AI, and quantum computing.

2

Watch It Unfold

Step through every computation at your own pace. See the code, the data structures, and the explanation — all in sync.

3

Build Real Intuition

Modify inputs, compare algorithms, and experiment until you truly understand how it works — not just what it does.

Built for Real Understanding

Not just pretty animations — every feature is designed to help you build genuine intuition about how algorithms work.

Every computation, at your own pace

Step-by-Step Playback

Play, pause, step forward, step backward, and scrub through any algorithm. Each step shows what changed and why — so you never lose track of the logic.

  • Frame-by-frame control with keyboard shortcuts
  • Variable speed from 0.25x to 4x
  • Scrub to any step instantly
Binary Search — Step 2 / 6
3
8
14
27
33
42
55
1Initialize low=0, high=6
2Compute mid = 3, check A[3]=27
327 < 42 → search right half

See the exact line being executed

Synchronized Code

Every visualization step highlights the corresponding line of code. The connection between what you see and how it works is never broken.

  • Line-level highlighting in real time
  • Variable state inspection on hover
  • Full source code for every algorithm
binary-search.js
1function binarySearch(arr, target) {
2  let low = 0, high = arr.length - 1;
3  while (low <= high) {
4    let mid = Math.floor((low+high)/2);
5    if (arr[mid] === target) return mid;
6    if (arr[mid] < target) low = mid+1;
7  }
8}
i

Line 4: Compute the midpoint index. Using Math.floor ensures an integer index when the array has even length.

Understand the why, not just the what

Plain-Language Explanations

Every step includes a human-readable explanation of what just happened. No jargon walls — just clear reasoning that builds genuine intuition.

  • Context-aware explanations for each step
  • Mathematical notation when helpful, plain English always
  • Key insight callouts for important moments
Self-Attention — Step 3 / 8
Attention Weights
The
cat
sat
down
0.1
0.7
0.1
0.1
0.2
0.2
0.4
0.2
0.1
0.3
0.1
0.5
0.1
0.1
0.6
0.2
?

What's happening: The word "cat" attends most strongly to "The" (0.7) because the model has learned that determiners modify the next noun. This is how self-attention builds context.

Four Domains, One Platform

From sorting algorithms to self-attention — explore every domain with the same interactive, step-by-step experience.

Classical Algorithms

The foundations of computer science

Binary search, sorting, graph traversal, and shortest paths — visualized step by step with full code synchronization.

Binary SearchQuickSortMerge SortBFSDFSDijkstra
7 algorithms

Deep Learning

Neural networks from neuron to network

Watch signals propagate through neurons, see backpropagation compute gradients, and understand convolution at the pixel level.

PerceptronFeedforwardBackpropConvolutionGradient Descent
5 algorithms

Generative AI

Transformers and attention, demystified

See how text becomes tokens, tokens become embeddings, and attention computes which words matter to each other.

TokenizationEmbeddingsSelf-AttentionMulti-HeadTransformer
5 algorithms

Quantum Computing

Qubits, gates, and superposition

Bloch spheres, quantum gates, and algorithms like Grover's search — visualized in ways that build real intuition.

Bloch SphereQuantum GatesGrover's SearchTeleportation
5 algorithms

Use It Your Way

Build custom visualizations in the browser editor, or integrate into your existing Python and JavaScript workflows.

Custom Algorithm Editor

Write JavaScript using the step() API. Choose from 13 built-in visualization layouts.

my-algorithm.js
const arr = [14, 27, 3, 42];
for (let i = 0; i < arr.length; i++) {
  step({ title: `Check ${i}` });
}
  • Sandboxed execution with real-time visualization
  • 6 starter templates · Share via URL
Try the Editor →

Python & npm Packages

Use the same visualizations in Jupyter notebooks, Python scripts, or any JavaScript project.

example.py
import eigenvue
eigenvue.show("self-attention")
eigenvue.jupyter("transformer")
pip install eigenvuenpm install eigenvue
Read the Docs →

Start Exploring Now

No account needed. No installation required. Pick an algorithm and start learning.

Browse AlgorithmsStar on GitHub