On Device Ai Python Packages

circle-schema

On-device Neural Engine

14K 570 180

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.

9K 1K 80

onert

On-device Neural Engine

7K 570 180

nobodywho

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

3K 914 60

sg1ab

nnfw_api binding

3K 570 180

m5-infer

Extraordinary speed, extraordinary quality — MLX-based inference engine for Apple Silicon.

2K 0 1

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.

1K 16 2

model-explorer-circle

On-device Neural Engine

1K 570 180

notolog

Notolog - Python Markdown Editor

738 25 6

mesh-cognition

Python coupling kernel for Mesh Cognition — per-field admission and state blending for CfC neural networks. Canonical home: meshcognition.org

657 0 0

edgetam-dimos

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

552 923 74

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.

389 1K 81

wildedge-sdk

Python SDK for WildEdge

310 14 1

memme

Edge-first AI memory engine. Rust core, DuckDB single-file, sub-10ms search, 6 language bindings.

169 105 9

nexaai-metal

Run frontier LLMs and VLMs with day-0 model support across GPU, NPU, and CPU, with comprehensive runtime coverage for PC (Python/C++), mobile (Android & iOS), and Linux/IoT (Arm64 & x86 Docker). Supporting OpenAI GPT-OSS, IBM Granite-4, Qwen-3-VL, Gemma-3n, Ministral-3, and more.

127 8K 999

langchain-mesh-cognition

LangChain integration for Mesh Cognition — give any agent distributed memory across devices

106 0 0

nexaai-gpu

71 8K 999

nexai

51 8K 999

nnfw-api-pybind

On-device Neural Engine

3 570 180