Metadata-Version: 2.4
Name: localkin
Version: 0.1.0
Summary: The LocalKin family in one install: kinfer (local LLM serving), OllamaDiffuser (images and video) and LocalKin Audio (speech)
Author-email: LocalKinAI Team <contact@localkin.ai>
License: MIT
Project-URL: Homepage, https://www.localkin.app
Project-URL: Source, https://github.com/LocalKinAI
Project-URL: kinfer, https://github.com/LocalKinAI/kinfer
Project-URL: OllamaDiffuser, https://github.com/LocalKinAI/ollamadiffuser
Project-URL: LocalKin Audio, https://github.com/LocalKinAI/localkin-service-audio
Keywords: local-ai,llm,inference,stable-diffusion,text-to-speech,speech-to-text,ollama,apple-silicon,localkin
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: End Users/Desktop
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Multimedia :: Graphics
Classifier: Topic :: Multimedia :: Sound/Audio :: Speech
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: kinfer-ai>=0.2.4; sys_platform == "darwin" and platform_machine == "arm64" and ("Kernel Version 25." in platform_version or "Kernel Version 26." in platform_version or "Kernel Version 27." in platform_version)
Requires-Dist: ollamadiffuser>=2.5.0
Requires-Dist: localkin-service-audio>=2.1.6
Dynamic: license-file

# LocalKin

[![PyPI](https://img.shields.io/pypi/v/localkin)](https://pypi.org/project/localkin/)
[![Downloads](https://img.shields.io/pepy/dt/localkin)](https://pepy.tech/project/localkin)

**The LocalKin family in one install.** Local AI that runs on your own machine —
language models, images and video, speech — with no cloud account and no
background service to keep alive.

```bash
pip install localkin
```

That installs every member below. Each is also its own package, so to install
only one, install it by name — `pip install kinfer-ai`, for example.
`python -m localkin` lists the family and which of it is installed.

## The family

| Package | Command | What it does |
|---|---|---|
| [kinfer-ai](https://pypi.org/project/kinfer-ai/) | `kinfer` | Local LLM serving for agent fleets: one binary with llama.cpp inside, speaking the Ollama, OpenAI, Anthropic and Responses APIs; models bigger than the machine read from the SSD. Apple Silicon, macOS 26. |
| [ollamadiffuser](https://pypi.org/project/ollamadiffuser/) | `ollamadiffuser` | Local image and video generation with an Ollama-style CLI: Stable Diffusion, FLUX, Qwen-Image, LTX — on MLX on a Mac, on diffusers elsewhere. |
| [localkin-service-audio](https://pypi.org/project/localkin-service-audio/) | `kin audio` | Local speech: speech-to-text and text-to-speech, Chinese included, voice cloning, an MCP server for Claude. |

kinfer runs on Apple Silicon with macOS 26 and is left out elsewhere; the other
two need Python 3.10 or newer and bring PyTorch with them.

More LocalKin tools — KinClaw, kinbrowser, kinrec and the rest, written in Go —
are on [localkin.app](https://www.localkin.app). The `localkin` command itself is
the agent runtime, [LocalKinAI/localkin](https://github.com/LocalKinAI/localkin),
installed with `go install`; this package installs no command of its own.

## License

MIT. Each member carries its own license: kinfer is Apache-2.0, OllamaDiffuser
and LocalKin Audio are MIT.
