A clean, lightweight music player for macOS.

gmc is a CLI tool that uses an LLM to generate high-quality Git messages and streamline related workflows.

RouterArena: An open framework for evaluating LLM routers with standardized datasets, metrics, an automated framework, and a live leaderboard.

A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future …

MCP 资源精选， MCP指南，Claude MCP，MCP Servers, MCP Clients

An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

在大陆地区使用普通银联信用卡通过 Apple Store 订阅 ChatGPT Plus 等产品的一些实践

A cross-platform desktop All-in-One assistant tool for Claude Code, Codex & Gemini CLI.

Public repository for Agent Skills

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

DigitalPlat FreeDomain: Free Domain For Everyone

📥 A Telegram toolkit written in Golang

Fast ML inference & training for ONNX models in Rust

High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.

🐹 Deep clean and optimize your Mac.

Generate jsonschemas from helm charts.

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

func-e (pronounced funky) makes running Envoy® easy

hpc 教程，包含集合通信(mpi、nccl)、cuda 编程、向量化 SIMD、RDMA 通信等

Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).

人人都能用英语

Open Source Landscapes and Insights Produced by AntOSS

​​Unlimited-length talking video generation​​ that supports image-to-video and video-to-video generation

A full-featured web-based Claude Code client that provides complete interactive functionality for managing Claude Code projects

Build and run tiny vms from Dockerfiles. Small and sleek.

SWE-bench: Can Language Models Resolve Real-world Github Issues?

GGUF Quantization support for native ComfyUI models

Efficient Mixture of Experts for LLM Paper List

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.