Search Packages

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.

circle-schema

On-device Neural Engine

onert

onert API binding

nobodywho

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

sg1ab

On-device Neural Engine

m5-infer

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

notolog

Notolog Markdown Editor

wildedge-sdk

Python SDK for WildEdge

mesh-cognition

Python coupling kernel for Mesh Cognition — per-field admission and state blending for CfC neural networks

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.

model-explorer-circle

Model Explorer Circle Adaptor

memme

Edge-first AI memory engine powered by DuckDB

edgetam-dimos

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

langchain-mesh-cognition

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

nexaai-metal

Nexa AI SDK

nexaai-gpu

Nexa AI SDK

nexai

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.