AI Copilot for Vim/NeoVim

A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface.

Unified management and routing for llama.cpp, MLX and vLLM models with web dashboard.

Build an Autonomous Web3 AI Trading Agent (BASE + Uniswap V4 example)

Experimental: MLX model provider for Strands Agents - Build, train, and deploy AI agents on Apple Silicon.

Reinforcement learning for text generation on MLX (Apple Silicon)

An all-in-one LLMs chat Web UI based on the MLX framework, designed for Apple Silicon.

Various LLM resources and experiments

Add MLX support to Pydantic AI through LM Studio or mlx-lm, run MLX compatible HF models on Apple silicon.

Federated Fine-Tuning of LLMs on Apple Silicon with Flower.ai and MLX-LM

A comprehensive toolkit for end-to-end continued pre-training, fine-tuning, monitoring, testing and publishing of language models with MLX-LM

LLM model inference on Apple Silicon Mac using the Apple MLX Framework.

Swift app to summarize YouTube content using AI

MLX inference service compatible with OpenAI API, built on MLX-LM and MLX-VLM.基于MLX-LM和MLX-VLM构建的OpenAI API兼容的MLX推理服务.

🤖 Run Strands Agents on Apple Silicon with ease—perform inference, fine-tune models, and leverage vision capabilities using Python and LoRA training.

A simple mlx-lm proxy server for gpt-oss

This is the part 2 of a GraphRAG system, in which the user interacts with the data through 2 data structures: vector database (Chroma DB) and graph database (Neo4j). I exploit the probabilism of vector embedding and the determinism of a knowledge graph to minimise hallucination and maximise explainability. The domain: ‘Electronic’ music genre.

OFX File Creator is a compact Python library/CLI that converts CSV/Excel bank exports into valid OFX statements. It normalizes vendor columns, parses dates and amounts, infers TRNTYPE via configurable YAML/JSON rules (optional mlx-lm enrichment), and includes examples, tests, and GitHub Actions CI.

Prompt LLM Bench is a platform that discovers compatible Hugging Face models on-the-fly, runs reproducible multi-model evaluations, and recommends the optimal prompt–LLM pair based on accuracy, latency, and resource efficiency.

Fine-tuning open-source LLMs for Corerefence Resolution task using mlx-lm