On Device Ai Python Packages

litert-lm-builder

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

litert-lm-api

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

litert-lm

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

circle-schema

On-device Neural Engine

mlx-tune

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.

litert-lm-builder-nightly

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

onert

On-device Neural Engine

litert-lm-api-nightly

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

litert-lm-nightly

LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.

mlx-speech

Pure-MLX speech synthesis, voice cloning, dialogue, sound-effects, and ASR for Apple Silicon: Fish S2 Pro, VibeVoice, LongCat, MOSS, Step-Audio, Cohere ASR.

coreai-catalog

Source-grounded registry of Apple Core AI models, artifacts, upstreams, benchmarks, and provenance.

nobodywho

NobodyWho is an inference engine that lets you run LLMs locally and efficiently on any device.

sg1ab

On-device Neural Engine

model-explorer-circle

On-device Neural Engine

apple-fm-mcp

MCP server exposing Apple Foundation Models to Claude Code and Claude Desktop. On-device AI, zero cost, fully private.

notolog

Notolog Markdown Editor

needle-rs

258 KB WASM runtime for Needle a 26M-parameter tool-calling transformer. Runs in browser, Cloudflare Workers, and Node.js. No backend required.

automaton-tnt

Terminal voice-to-text TUI — Qwen3-ASR-1.7B on the Apple GPU via MLX (mlx-speech). Fully local, no PyTorch, transcribes in ~1s. macOS Apple Silicon.

cactus-compute-test

Low-latency AI engine for mobile devices & wearables

wildedge-sdk

ML inference monitoring for Python: on-device and remote models

heed-wakeword

Tiny, custom, on-device wake-word detection. Train your own in seconds, deploy anywhere (Python / browser / mobile).

voxrt-wake-word

On-device wake-phrase detection for Linux aarch64 — one glibc-2.17 .so behind Python (PyPI wheel), Node.js (npm), Go (go get), C/C++ (tarball + CMake), Rust. RTF 0.053 on Raspberry Pi Zero 2 W. Same runtime as voxrt-wake-word-{android,ios}.

edgetam-dimos

[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"

unsloth-mlx

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.