Metadata-Version: 2.4
Name: localmind-bench
Version: 0.1.0
Summary: Hardware benchmarking tool for the LocalMind adaptive AI runtime
Project-URL: Homepage, https://github.com/atunraseayomide/localmind
Project-URL: Repository, https://github.com/atunraseayomide/localmind
Project-URL: Bug Tracker, https://github.com/atunraseayomide/localmind/issues
Author-email: Atunrase Ayo <atunraseayomide@gmail.com>
License: MIT
Keywords: benchmark,edge-ai,hardware,inference,llm,local-ai,localmind,profiler
Classifier: Development Status :: 3 - Alpha
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.10
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: System :: Hardware
Classifier: Topic :: Utilities
Requires-Python: >=3.10
Requires-Dist: numpy>=1.24
Requires-Dist: psutil>=5.9
Requires-Dist: py-cpuinfo>=9.0
Requires-Dist: rich>=13.0
Requires-Dist: typer>=0.12
Description-Content-Type: text/markdown

# localmind-bench

Hardware benchmarking tool for the LocalMind adaptive AI runtime.

`localmind-bench` profiles any machine and generates a JSON dataset that
LocalMind's strategy planner will use to make intelligent model-routing decisions.

## What it measures

| Category | Fields |
|---|---|
| CPU | Model, core count, max frequency, architecture |
| RAM | Total, available, used % |
| Storage | Type (SSD/HDD/NVMe), total, free |
| GPU | Available, name, VRAM, backend (cuda/mps/none) |
| OS | System, version, machine |
| Capacity | Live RAM headroom, SSD read speed, CPU matmul score |

## Install

```bash
cd packages/localmind-bench
pip install -e .
```

## Run

```bash
localmind-bench profile
```

Output is printed to the terminal and saved to `localmind_bench_profile.json`
in the current working directory.
