Skip to content

SuperQuantX Documentation

SuperQuantX

Experimental Quantum ML Toolkit

No hype. Checked results.

One API across quantum SDKs, with a classical baseline for every result.

Welcome to SuperQuantX

SuperQuantX is an experimental, open-source toolkit for quantum machine learning and optimisation research. One API runs the same circuits and algorithms on PennyLane, Qiskit, Cirq, Amazon Braket, pytket and a built-in simulator, and every result comes with a classical reference so you can see whether the quantum part earns its keep.

Key features

  • One API, six gate-model backends: identical circuits, bit order normalised across SDKs.
  • Algorithms with built-in checks: VQE reports the exact ground energy, QAOA reports the brute-force optimum, classifiers can be benchmarked with compare_to_classical.
  • Research-grade benchmarking: equal tuning budgets, identical folds and a corrected t-test, following arXiv:2610.42029.
  • Agents that show their work: portfolio and classification agents return the classical optimum or baseline alongside the quantum answer.
SuperQuantX Logo

What works today

Backend Status
Built-in simulator tested
PennyLane (default.qubit) tested
Qiskit (Aer) tested
Cirq simulator tested
Amazon Braket LocalSimulator tested
pytket local simulator tested
D-Wave Ocean QUBO/Ising only
IBM Quantum, Braket devices, Quantinuum hardware untested, needs your own credentials
Azure Quantum, Rigetti Forest, cuQuantum, TensorFlow Quantum planned, not implemented

See the Showcase for real output from every tested backend.

Quick Start

Get started with SuperQuantX in minutes:

import superquantx as sqx

# Choose your backend
backend = sqx.get_backend('simulator')

# Create a quantum circuit
circuit = backend.create_circuit(n_qubits=2)
circuit = backend.add_gate(circuit, 'H', 0)  # Hadamard gate
circuit = backend.add_gate(circuit, 'CNOT', [0, 1])  # CNOT gate
circuit = backend.add_measurement(circuit)

# Execute the circuit
result = backend.execute_circuit(circuit, shots=1024)
print(f"Results: {result['counts']}")

📚 Getting Started

Learn the basics and get up and running quickly.

👨‍💻 User Guide

Comprehensive guides for using SuperQuantX.

🧪 Tutorials

Hands-on tutorials and examples.

📖 API Reference

Complete API documentation.

📏 Results

Real output, checked against classical baselines.

Research Areas

SuperQuantX accelerates research in:

  • Quantum Machine Learning: QSVM, QNN, quantum feature maps
  • Quantum Optimization: QAOA, VQE (including CVaR-VQE), quantum annealing via D-Wave Ocean
  • Quantum Agents: Portfolio and classification agents with classical checks
  • Honest evaluation: Tuned classical baselines and significance tests for every quantum model

Community & Support

Built with ❤️ for the Quantum AI research community

Developed by Superagentic AI