PyRe 1.1 · Available Now · Windows x64

Your Python.
A steadier run.

Keep your workload on your machine. PyRe brings resource planning, conservative routing, a durable controller, and run evidence to local Python execution. Run verified CPU, NVIDIA CUDA, AMD ROCm and Intel XPU jobs with output parity and receipt logging. Every subscription includes Wittlet Desktop Companion free ($12 value).

Confirmed in 1.1 — Preconfigured GPU environments: pyre --env lists and activates nvidia-cuda, amd-rocm, intel-oneapi, apple-mps, cpu presets.

ROCm + XPU lanes — AMD and Intel stacks are detected from system tools and scheduled once a matching framework interpreter is configured.

Offline subscriptions — Monthly ($3.99) or yearly ($29.99). Fully offline Ed25519 device-bound license; no runtime network.

$29.99 USD / year · 1-Year Subscription (or $3.99/mo) · Includes Wittlet

Subscribe to PyRe ($29.99/yr) Desktop Preview Download proof script

Native Windows Desktop Workbench

Real-Time Execution Controller

Manage sequential or parallel script runs with live CPU and GPU allocation gauges, process supervision, and atomic run receipts.

PyRe 1.1 runs CPU, NVIDIA CUDA, and — with a matching environment — AMD ROCm and Intel XPU jobs. Use pyre --env to detect installed stacks and activate the right preset.

Plan the run. Follow the evidence.

CPU first

Automatic routing keeps ambiguous workloads on the CPU. A supported accelerator is an option for compatible code—not a promise that ordinary Python becomes GPU code.

Know the budget

Inspect hardware and an allocation plan before starting work. Leave capacity for the operating system and other applications.

Keep a run record

Durable status and recovery records help explain what started, what finished, and what needs attention. Missing evidence should stay unknown.

Measure the whole job

Choose acceleration using representative inputs, matching outputs, and total time—including transfers. A faster kernel does not always mean a faster program.

Bring your own workload.

PyRe is an execution controller, not a chat model or a security sandbox. Run only code and commands you trust. It does not rewrite ordinary Python or move data to a GPU for you.

The PySide6 desktop submits work to the same durable local controller used for resource admission, execution, status, recovery, and receipts. Current protected host acceptance passed on Windows x64 with CPython 3.10, 3.11, 3.12, and 3.13. Actual CPU/CUDA execution and output parity passed on an NVIDIA GeForce RTX 5070 Ti. These results describe the tested configurations, not every GPU or workload.

Optional acceleration still depends on compatible code, the operating system, an officially supported device and driver, and a matching framework build. PyRe 1.1 is available now for Windows x64 with a subscription at $29.99 USD/year or $3.99/month and includes Wittlet Desktop Companion free ($12 value).

Run code on the device you selected.

PyRe reserves and launches the selected lane. Your workload must explicitly create or move tensors on that device. Start with the downloadable CPU/GPU proof script; set its BACKEND constant to match the mode you choose in PyRe. Its CPU path uses only the Python standard library, while its optional accelerator path imports PyTorch, checks the real runtime device, includes transfers and synchronization in timing, compares output with CPU, and exits with an error instead of silently falling back.

Create a separate virtual environment for the accelerator and install both PyRe and the framework build that matches the operating system, driver, and device. Use the current official PyTorch installer selector. Intel users should also follow the official PyTorch XPU guide. Windows AMD users must check the exact GPU, Python, PyTorch, and ROCm combination in AMD's official Windows support matrix.
Before starting the controller, set the matching absolute interpreter path: PYTHON_GPU_CUDA_PYTHON, PYTHON_GPU_XPU_PYTHON, or PYTHON_GPU_ROCM_PYTHON. The current desktop Settings dialog shows these effective paths; it does not install frameworks or change them for a controller that is already running.
Set BACKEND near the top of how-to.py to "cpu", "cuda", "xpu", or "rocm". In PyRe, add that file, choose the matching mode and physical device, and select Check backend. A backend check proves current framework/device identity, not that arbitrary code will accelerate.
Select Run selected. In the controller output and receipt, confirm the requested and selected backend. The example also prints actual_device, parity=PASS, and transfer-inclusive elapsed time. AMD ROCm PyTorch intentionally uses the torch.cuda Python API and verifies that the runtime reports HIP.

# PowerShell — replace this placeholder with the absolute GPU-environment interpreter
$env:PYTHON_GPU_CUDA_PYTHON = "C:\path\to\gpu-venv\Scripts\python.exe"
& ".\Launch PyRe.cmd"

Start PyRe from that same PowerShell session so the controller inherits the CUDA setting. The XPU and ROCm variables are reference configuration only; they do not enable scheduling in the current desktop release.

Choose an explicit accelerator mode when GPU execution is required. Auto keeps ambiguous work on CPU. PyRe does not promise OpenCL, DirectML, Vulkan, Apple GPU support, or automatic conversion of CPU code.

Accelerator status

Lane	Support designed	Verified now
CPU	Standard Python and CPU framework workloads	Protected Windows x64 host acceptance passed on CPython 3.10–3.13
NVIDIA CUDA	Explicit CUDA through a matching PyTorch environment and selected physical device	Actual CPU/CUDA execution and parity passed on an RTX 5070 Ti; this does not cover every NVIDIA GPU
Intel XPU	Explicit XPU adapter, interpreter probe, device identity, and reservation; preconfigured `intel-oneapi` environment	Schedulable in 1.1 with an XPU PyTorch build; physical Intel GPU acceptance NOT_CHECKED on this host
AMD ROCm	Explicit ROCm adapter using PyTorch's CUDA-compatible Python API, device identity, and reservation; preconfigured `amd-rocm` environment	Schedulable in 1.1 with a HIP PyTorch build; physical AMD GPU acceptance NOT_CHECKED on this host. Windows framework support is limited to AMD's current matrix

Transparent Subscription Pricing

Choose Your Setup

All plans include the complete native Windows workbench, continuous verification updates, Wittlet Desktop Companion free ($12 value), and immediate digital delivery.

PyRe 1.1 for Windows

For Python developers and ML practitioners who want dependable local execution.

$29.99 USD / year · 1-Year Subscription (or $3.99/mo)

✓ Windows 10/11 x64 desktop workbench
✓ CPython 3.10, 3.11, 3.12, 3.13 verified
✓ NVIDIA CUDA, AMD ROCm, Intel XPU lanes
✓ Preconfigured GPU environments (pyre --env)
✓ CPU-first fallback and resource allocation planning
✓ Wittlet Desktop Companion included free ($12 value)
✓ Offline Ed25519 device license (100% offline verification)
✓ 1-Year Subscription ($29.99/yr) or Monthly ($3.99/mo)
✓ Signed installer download + email receipt

Wittlet Included Free

PyRe + Wittlet Bundle

Combine local Python execution with our private desktop AI companion.

$29.99 USD / year · Wittlet ($12/yr value) included free

✓ Everything in PyRe 1.1 for Windows
✓ Wittlet Local AI Companion (Included Free, $12 value)
✓ 10 customizable characters & 8 colorways
✓ Offline private CPU chat, brainstorming, drafting
✓ Guarded approved-folder find, open & proposals
✓ Unified bundle access or separate setup
✓ PyRe $29.99/yr · Wittlet included at no extra charge

Subscribe to PyRe + free Wittlet ($29.99/yr)

Wittlet standalone is $12/year (or $0.99/mo).

How Offline Subscription Enforcement Works

PyRe operates completely offline on your local machine without needing an internet connection to schedule, route, or inspect Python runs. Subscriptions are enforced through our proven cryptographic model:

Ed25519 Asymmetric Signatures: When you subscribe or renew, our commerce service generates an authentic cryptographically signed license file. The signature is mathematically impossible to forge without our private key.
Hardware Fingerprinting: Licenses bind to your Windows installation identity (MachineGuid), ensuring licenses stay locked to your licensed hardware.
100% Offline Validation: PyRe's controller validates the signature and active subscription dates locally with its embedded public key. Zero telemetry, zero cloud pings, zero privacy leakage.

Release 1.1.0 is available for Windows x64.

PyRe 1.1 is published and available for immediate subscription and download. The native Windows x64 package is built with encrypted release distribution and authenticated via Hugging Face and Fly.io.

A subscription at $29.99 USD/year or $3.99/month via Stripe entitles you to active use of PyRe, continuous updates, and Wittlet Desktop Companion free ($12 value). Immediately after payment, a secure download link, receipt, and offline license are delivered to your email.

Subscribe to PyRe ($29.99/yr) Customer Access & Redownload Contact Support

Your Python.A steadier run.