Stars
My continuously updated Machine Learning, Probabilistic Models and Deep Learning notes and demos (2000+ slides) 我不间断更新的机器学习，概率模型和深度学习的讲义(2000+页)和视频链接
Ulysses sequence-parallel all-to-all as a torch custom op, moved by the GPU copy engines into torch symmetric memory. Zero SM usage; 1.66-2.17x over torch.distributed on NVLink.
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
AI coding agent skill for deep architectural analysis of open-source projects | 开源项目深度架构分析，一句话生成专业级分析报告
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
Deep dive into Claude Code's source code— learn from the best agent implementation out there.
深入Claude Code源码，学习目前最好的agent实现
CheetahClaws: A Fast and Easy-to-Use Agent Harness Infrastructure for Long-Horizon, Multi-Model, and Tool-Using AI Systems
🔥 A collection of the Claude Code open source
Ultra-light Harness scaffolding for AI agents, a mini version of claude code
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
TradingAgents: Multi-Agents LLM Financial Trading Framework
Codexs - OpenAI Account Batch Generator & Codex Tools Importer
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
🚀 Efficient implementations for emerging model architectures
OpenClaw 的中国IM平台整合Docker版本，预装并配置了飞书、钉钉、QQ机器人、企业微信等主流中国IM软件的插件，让您可以快速部署一个支持多个中国IM平台的 AI 机器人网关
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Your Personal AI Assistant; easy to install, deploy on your own machine or on the cloud; supports multiple chat apps with easily extensible capabilities.
Algorithm powering the For You feed on X
Tiny-Megatron, a minimalistic re-implementation of the Megatron library
Tiny-DeepSpeed, a minimalistic re-implementation of the DeepSpeed library
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
A framework for efficient model inference with omni-modality models
NexusTrader is a professional-grade open-source quantitative trading platform designed by Scott Zhang
注释的nano_vllm仓库，并且完成了MiniCPM4的适配以及注册新模型的功能