Stars
Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
You're the CTO, agents are your team. They handle tasks on their own, message each other, and review each other's work. You just watch the kanban board and give high-level commands. Codex/Claude/Op…
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
IntelliJ-style Git experience for VS Code. A full-featured Git GUI with commit graph visualization, branch management, intelligent file staging, and a shelf (stash) system — all designed to match t…
Solved LeetCode problem in VS Code added some new features
A collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。
My learning notes for ML SYS.
GitHub's code repository is all you need
The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.
OpenClaw专用量化投资知识库：策略、技术指标、社媒情绪分析、风控模型
基于天勤量化TqSdk实现的期货量化交易策略集合，含双均线、布林带、RSI、Dual Thrust、海龟策略，附完整中文注释
CTA程序化交易策略踩坑系列 - 使用VeighNa Trader回测
Binance trading gateway for VeighNa Evo
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, i…
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi…
[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant
Your AI's shortcut to mass-produce alpha-generating quant strategies.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…
The open agent skills tool - npx skills
Dr. MAS is an end-to-end RL training framework for multi-agent LLM systems, supporting the co-training of multiple (heterogeneous) LLMs.
A high-throughput and memory-efficient inference and serving engine for LLMs
Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill c…