Metadata-Version: 2.4
Name: mlx-cv
Version: 0.0.1
Summary: MLX-native computer vision for Apple Silicon: object detection, segmentation, and open-vocabulary grounding.
Project-URL: Homepage, https://github.com/appautomaton/mlx-cv
Project-URL: Repository, https://github.com/appautomaton/mlx-cv
Project-URL: Issues, https://github.com/appautomaton/mlx-cv/issues
Author-email: AppAutomaton <brian@bhoneycutt.com>
License-Expression: MIT
License-File: LICENSE
Keywords: apple-silicon,computer-vision,locate-anything,mlx,object-detection,open-vocabulary,sam,segmentation
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Operating System :: MacOS
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: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Image Recognition
Classifier: Typing :: Typed
Requires-Python: >=3.9
Description-Content-Type: text/markdown

# mlx-cv

**MLX-native computer vision for Apple Silicon** — object detection, segmentation, and open-vocabulary grounding.

[![PyPI](https://img.shields.io/pypi/v/mlx-cv.svg)](https://pypi.org/project/mlx-cv/)
[![Python](https://img.shields.io/pypi/pyversions/mlx-cv.svg)](https://pypi.org/project/mlx-cv/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)

> ⚠️ **Pre-alpha / placeholder.** This release reserves the package name. The public API is not yet defined and will change without notice.

## What is this?

`mlx-cv` aims to be the detection & segmentation layer for the [MLX](https://github.com/ml-explore/mlx) ecosystem — sitting alongside `mlx-lm` and `mlx-vlm`, but focused on computer-vision tasks that run natively and efficiently on Apple Silicon.

### Planned model support

- **SAM 3** — promptable segmentation
- **LocateAnything** — open-vocabulary detection / localization
- …and more detection / grounding architectures over time

## Installation

```bash
pip install mlx-cv
```

> Requires Python 3.9+ and an Apple Silicon Mac (for the eventual MLX runtime).

## Status

| Stage | Status |
|-------|--------|
| Name reserved on PyPI | ✅ |
| Public API | 🚧 in design |
| First model port | 🚧 planned |

## License

[MIT](LICENSE) © AppAutomaton
