Metadata-Version: 2.5
Name: localm
Version: 0.2.0
Summary: Local AI platform - offline LLM inference, model management, and extensible agent plugins
Project-URL: Homepage, https://github.com/Matlan1/localm
Project-URL: Repository, https://github.com/Matlan1/localm
Project-URL: Issues, https://github.com/Matlan1/localm/issues
Project-URL: Changelog, https://github.com/Matlan1/localm/blob/master/CHANGELOG.md
Author: Matlan1
License: AGPL-3.0-or-later
License-File: LICENSE
Keywords: agent,gguf,inference,llama,llm,local,mcp,offline
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Environment :: Web Environment
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)
Classifier: Operating System :: Microsoft :: Windows
Classifier: Operating System :: POSIX :: Linux
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Code Generators
Requires-Python: <3.13,>=3.12
Requires-Dist: certifi>=2026.7.22
Requires-Dist: click>=8.5.0
Requires-Dist: cryptography>=50.0.1
Requires-Dist: fastapi>=0.141.1
Requires-Dist: huggingface-hub>=1.29.0
Requires-Dist: pillow>=12.3.0
Requires-Dist: pydantic>=2.13.5
Requires-Dist: pywin32>=311; sys_platform == 'win32'
Requires-Dist: qrcode>=8.2
Requires-Dist: regex>=2026.8.31
Requires-Dist: requests>=2.31
Requires-Dist: rich>=15.0.0
Requires-Dist: starlette>=1.6.0
Requires-Dist: uvicorn>=0.52.4
Requires-Dist: zeroconf>=0.150.0
Provides-Extra: audio
Requires-Dist: soundfile>=0.14.0; extra == 'audio'
Provides-Extra: browser
Requires-Dist: playwright<1.62,>=1.61; extra == 'browser'
Provides-Extra: coder
Requires-Dist: requests>=2.31; extra == 'coder'
Provides-Extra: cpu
Provides-Extra: desktop
Requires-Dist: pywebview>=6.2.1; (sys_platform == 'win32' or sys_platform == 'darwin') and extra == 'desktop'
Requires-Dist: pywebview[qt]>=6.2.1; (sys_platform == 'linux') and extra == 'desktop'
Provides-Extra: dev
Requires-Dist: psutil>=7.2.2; extra == 'dev'
Requires-Dist: pypdf>=6.16.1; extra == 'dev'
Requires-Dist: pytest-cov>=5.0; extra == 'dev'
Requires-Dist: pytest-xdist>=3.6; extra == 'dev'
Requires-Dist: pytest>=8.0; extra == 'dev'
Requires-Dist: ruff>=0.16.5; extra == 'dev'
Requires-Dist: zizmor>=1.30.0; extra == 'dev'
Provides-Extra: gpu
Requires-Dist: accelerate>=1.14.0; extra == 'gpu'
Requires-Dist: psutil>=7.2.2; extra == 'gpu'
Requires-Dist: rocm-sdk-core; (sys_platform == 'win32') and extra == 'gpu'
Requires-Dist: rocm-sdk-libraries-gfx103x-all; (sys_platform == 'win32') and extra == 'gpu'
Requires-Dist: rocm; (sys_platform == 'win32') and extra == 'gpu'
Requires-Dist: tokenizers==0.22.2; extra == 'gpu'
Requires-Dist: torch==2.11.0+rocm7.13.0; (sys_platform == 'win32') and extra == 'gpu'
Requires-Dist: torchvision==0.26.0+rocm7.13.0; (sys_platform == 'win32') and extra == 'gpu'
Requires-Dist: transformers[kernels]~=5.15.1; extra == 'gpu'
Provides-Extra: grammar
Requires-Dist: triton-windows>=3.7; (sys_platform == 'win32') and extra == 'grammar'
Requires-Dist: xgrammar>=0.2.2; extra == 'grammar'
Provides-Extra: monitor
Requires-Dist: psutil>=7.2.2; extra == 'monitor'
Provides-Extra: rag
Requires-Dist: pypdf>=6.16.1; extra == 'rag'
Provides-Extra: voice
Requires-Dist: faster-whisper>=1.2.1; extra == 'voice'
Description-Content-Type: text/markdown

# LocaLM

Run large language models on your own machine. Offline, private, and yours.

LocaLM downloads and runs LLMs locally: GGUF models through llama.cpp and
HuggingFace models through transformers, on AMD, NVIDIA, Intel, Apple Silicon
or CPU. It ships a chat GUI, an OpenAI-compatible API, a coding agent, RAG
over your own documents, and an MCP server, with everything off by default and
nothing leaving your machine.

## Install

```bash
pip install localm
localm setup-llama
```

`setup-llama` detects your GPU and provisions the matching llama.cpp runtime.
It needs no vendor toolkit: NVIDIA gets a self-contained CUDA build, AMD on
Windows a bundled ROCm build, Intel and toolkit-less AMD a Vulkan build, Apple
Silicon Metal, and anything else CPU.

Then pull a model and talk to it:

```bash
localm pull unsloth/Qwen3-4B-Instruct-2507-GGUF:Q4_K_M
localm run Qwen3-4B-Instruct-2507
```

Or open the graphical interface:

```bash
localm gui
```

Python 3.12 is required. `localm doctor` reports what is installed and what is
missing at any point.

## Where data lives

Set `LOCALM_HOME` to choose where models, chats and settings are stored. Left
unset, it defaults to a directory inside the Python environment you installed
into (not a per-user directory); `localm info` prints the path actually in
use.

## The self-contained installer

The pip package installs LocaLM into an environment you already manage. The
installer on GitHub instead provisions its own Python and its own private
environment, adds a desktop launcher and a native app window, and walks you
through choosing plugins. If you would rather have that, or you are not on
Python 3.12, use it:

<https://github.com/Matlan1/localm>

## Documentation, issues and source

<https://github.com/Matlan1/localm>

AGPL-3.0-or-later.
