Metadata-Version: 2.4
Name: axim-os
Version: 1.1.4
Classifier: Development Status :: 4 - Beta
Classifier: License :: Other/Proprietary License
Classifier: Operating System :: MacOS :: MacOS X
Classifier: Operating System :: POSIX :: Linux
Classifier: Operating System :: Microsoft :: Windows
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.9
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Rust
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: System :: Hardware
Requires-Dist: maturin>=1.5 ; extra == 'dev'
Requires-Dist: pytest>=7.0 ; extra == 'dev'
Requires-Dist: marimo>=0.9.0 ; extra == 'notebook'
Requires-Dist: torch>=2.0.0 ; extra == 'notebook'
Requires-Dist: torch>=2.6.0 ; extra == 'tpu'
Requires-Dist: torch-xla>=2.6.0 ; extra == 'tpu'
Provides-Extra: dev
Provides-Extra: notebook
Provides-Extra: tpu
License-File: LICENSE
Summary: AXIM OS — Universal CUDA-Free Compute & Graphics Runtime Engine by Cognitus Lab.
Keywords: axim,axim-os,aximos,cuda-free,vulkan,metal,simd,inference,synaxim,gpu,compute,graphics,gaming,heterogeneous,deep-fusion,jbound,fsm,tpu
Author: Cognitus Lab, GRRNMAKER
License: Proprietary: Cognitus Lab End User License Agreement (EULA)
Requires-Python: >=3.9
Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
Project-URL: Changelog, https://github.com/Cognitus-Lab/AximOS/blob/main/CHANGELOG.md
Project-URL: Homepage, https://github.com/Cognitus-Lab/AximOS
Project-URL: Issues, https://github.com/Cognitus-Lab/AximOS/issues
Project-URL: Repository, https://github.com/Cognitus-Lab/AximOS

# AXIM OS™

**Universal CUDA-Free Compute & Graphics Runtime Engine**  
*Copyright © 2026 Cognitus Lab. All Rights Reserved.*

---

## ⚡ Overview

**AXIM OS™** is an enterprise-grade, hardware-agnostic compute and graphics runtime engineered by **Cognitus Lab**. 

AXIM allows developers to deploy modern AI inference models, post-transformer architectures, and high-performance compute workloads across diverse accelerators without depending on proprietary vendor lock-in:

- **Apple Silicon (M1–M4):** Native Metal 3 execution with zero-copy unified memory residency.
- **NVIDIA & AMD GPUs:** High-throughput Vulkan compute & graphics pipelines with register-level kernel fusion.
- **Windows Systems:** DirectX 12 compute & rendering interfaces.
- **Host CPU SIMD:** Automated AVX-512, AVX2, and ARM NEON vectorization engines.

---

## 📦 Installation

Install the official precompiled runtime binary for your platform via `pip`:

```bash
pip install axim-os
```

Supported Platforms:
- **macOS** (Apple Silicon `arm64`, macOS 11.0+)
- **Linux** (`x86_64`, `manylinux_2_28`+)
- **Windows** (`x86_64`, Windows 10/11)

---

## 🚀 Quick Start

### 1. Command Line Interface (CLI)
After installing, verify detected hardware and available compute backends:

```bash
# Inspect system compute and graphics devices
axim info

# Verify runtime initialization
axim hello
```

### 2. Python API

```python
import axim

# Detect available hardware accelerators
devices = axim.detect_devices()
print("Available compute devices:", devices)

# Run kernel operations with automatic device dispatch
x = [1.0, 2.0, 3.0, 4.0]
y = [5.0, 6.0, 7.0, 8.0]
out = axim.add(x, y, device="auto")
print("Output:", out)
```

---

## 🔒 Enterprise Security & Intellectual Property

AXIM OS™ is distributed as a compiled, stripped binary runtime. It does not require or distribute raw source trees.

- **Execution-Only Model:** Distributed in the runtime execution model (analogous to the NVIDIA CUDA Toolkit or graphics display drivers) to execute user workloads locally on consumer and enterprise accelerators.
- **Zero Telemetry / Offline Execution:** AXIM OS runs entirely locally on your host and hardware without external dependencies.

---

## 📄 License & Terms

AXIM OS™ is proprietary software owned 100% exclusively by **Cognitus Lab**.

Licensed under the **Cognitus Lab End User License Agreement (EULA)**:
- Users are granted a limited, non-exclusive license solely to install and run the compiled binaries to execute workloads on their hardware.
- Sublicensing, resale, redistribution, copying, disassembling, decompiling, and reverse engineering are strictly prohibited.

For commercial licensing, enterprise support, or hardware integration, contact [Cognitus Lab](https://github.com/Cognitus-Lab).

