01
Make a plan
Choose your settings and set a limit before a test starts.
SUPERAGENTIC AI / QUANTUM RESEARCH
Run quantum AI experiments with results you can explain.
Try the free open source Python tools on your own computer. Run a small quantum test and inspect the results. If you want help, discuss an assisted pilot with us.
Free SDK. Local simulator. No account needed.
A REAL SAVED RESULT
LOCAL SIMULATORTwo qubits. One linked result.
This Bell test uses two simulated quantum bits. Across 1,024 measurements, both bits always had the same value.
| Both bits | Count | Share |
|---|---|---|
| 00 | 511 | 49.9% |
| 11 | 513 | 50.1% |
Saved with SDK 0.3.0 and seed 42. This is a computer model, not a live cloud test. It does not show that quantum methods beat standard ones.
Download the saved result (JSON)FREE / OPEN SOURCE / ON YOUR COMPUTER
Try SuperQuantX for free.
Install the open Python toolkit and run a small quantum simulator test yourself. The built in simulator needs no account, API key or credit card.
The SDK uses the Apache 2.0 licence. Read the code, use it and help improve it. Your own computer costs and any optional external provider charges still apply.
Prefer help with a study? Discuss an assisted pilot. Any pilot scope and fee are agreed separately.
Start with a Bell simulator test
Use Python 3.11 or newer in a fresh virtual environment. Install the version used by our recorded demo:
python -m pip install superquantx==0.3.0Follow the short example to run two simulated quantum bits. This is a computer model, not a quantum device.
Experimental research tools, not a production service. This example is not a speed or accuracy advantage claim. The automatic encoding benchmark in SDK 0.3.0 fails, and its nested data preparation needs review; read the current limits. See the official documentation for setup and optional packages.
A CLEAR PATH THROUGH THE WORK
02
Run a small test
Use the experimental SDK on your computer. Our site shows a recorded simulator example.
03
Share what you learn
Download the results and a report. Keep the limits of each test clear.
EVIDENCE BEFORE CLAIMS
A useful answer includes its limits.
A good research result says what was tested, how it ran and what it cannot tell us. We keep computer models, real hardware results and cost estimates separate. We do not claim a quantum speed or accuracy gain.
See what is ready and what needs work