Stars
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
Coding Agent singularly focused efficiency and context curation. Reduces API costs by 50-80% vs other agent AND improves the code quality at the same time. Uses Hash Anchored edits, massively paral…
reverse engineering Gemini's SynthID detection
Chrome DevTools for coding agents
Roo Code gives you a whole dev team of AI agents in your code editor.
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
Ming - facilitating advanced multimodal understanding and generation capabilities built upon the Ling LLM.
A lightweight text-to-speech model with zero-shot voice cloning
apt-mirror Python/asyncio reimplementation. Mirror of https://gitlab.com/apt-mirror2/apt-mirror2
Ubuntu, Alpine, Arch, and Fedora based Webtop images, Linux in a web browser supporting popular desktop environments.
Sharp Monocular View Synthesis in Less Than a Second
A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.
很多镜像都在国外。比如 gcr 。国内下载很慢，需要加速。致力于提供连接全世界的稳定可靠安全的容器镜像服务。
🚀2.3x faster than MinIO for 4KB object payloads. RustFS is an open-source, S3-compatible high-performance object storage system supporting migration and coexistence with other S3-compatible platfor…
The recursive internet scanner for hackers. 🧡
A cross-platform protocol library to communicate with iOS devices
Official GitHub repository for FLUX.1 Krea [dev].
A fork of Proxmox VE for ARM and LoongArch architectures
A high-throughput and memory-efficient inference and serving engine for LLMs
From Images to High-Fidelity 3D Assets with Production-Ready PBR Material
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
An extremely low latency KVMFR (KVM FrameRelay) implementation for guests with VGA PCI Passthrough.
A processing script for Bricklayers in Prusaslicer and Orcaslicer
A synthetic micro-benchmark that measures peak compute, bandwidth, and matrix throughput of GPUs and CPUs