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-fri…

Metal GPU implementation of the Qwen3 transformer model on macOS with complete Apple Silicon compute shader acceleration.

Tensor library for machine learning

A workshop that teaches you how to build your own coding agent. Similar to Roo code, Cline, Amp, Cursor, Windsurf or OpenCode.

A high-throughput and memory-efficient inference and serving engine for LLMs

Python bindings for llama.cpp

ControlNet++: All-in-one ControlNet for image generations and editing!

Portable file server with accelerated resumable uploads, dedup, WebDAV, FTP, TFTP, zeroconf, media indexer, thumbnails++ all in one file, no deps

LLM inference in C/C++

Run Orpheus 3B Locally With LM Studio

Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale…

TTS support with GGML

Faster Whisper transcription with CTranslate2

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Whisper realtime streaming for long speech-to-text transcription and translation

No fortress, purely open ground. OpenManus is Coming.

A cert-manager webhook to perform DNS01 challenge through websupport DNS API

A simple screen parsing tool towards pure vision based GUI agent

An open source personal productivity platform built on Markdown, turbo charged with the scripting power of Lua

🤗 smolagents: a barebones library for agents that think in code.

Simple, unified interface to multiple Generative AI providers

Everything about the SmolLM and SmolVLM family of models

Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Code for the paper "Language Models are Unsupervised Multitask Learners"

A collection of projects designed to help developers quickly get started with building deployable applications using the Claude API

Private & local AI personal knowledge management app for high entropy people.

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

llama3 implementation one matrix multiplication at a time