Stars
Suite of motion imitation methods for training motion controllers.
MCP server enabling AI assistants to author, edit, and print documents using LaTeX/Markdown with collaborative editing and project-based organization
Intelligent automation and multi-agent orchestration for Claude Code
🚀 Full-stack Next.js 15 + Cloudflare Workers template with D1 database, R2 storage, Better Auth, and Server Actions. Production-ready with automated CI/CD and generous free tiers.
文颜 MCP Server 可以让 AI 自动将 Markdown 文章排版后发布至微信公众号。
Obsidian Wechat public Plugin (微信公众平台) is a plugin to release article from your Obsidian Vault to WeChat, Baidu baiJiahao or other platforms.
Desktop app and API created in public for multi-agent Claude Code orchestration - coordinate local and remote agents through @mentions.
Official implementation of OpenWBT.
Kimi K2 is the large language model series developed by Moonshot AI team
Use Claude Code with any LLM provider - GLM-4.5, Kimi-K2, Qwen3-Coder, DeepSeek, etc.
The AI coding agent built for the terminal.
LLM Chess - Large Language Models Competing in Chess
An open-source AI agent that brings the power of Gemini directly into your terminal.
Official Lean AI Native Companies Leaderboard: The Future of 1-Person Billion-Dollar Startups
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards
Technical report of Kimina-Prover Preview.
NVIDIA Isaac GR00T N1.5 - A Foundation Model for Generalist Robots.
Reproducing R1-Zero-like Reforcement Learning on GSM8K Using Unsloth
A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning
MLGym A New Framework and Benchmark for Advancing AI Research Agents
MoBA: Mixture of Block Attention for Long-Context LLMs
[RSS 2025] "ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills"
"AutoAgent: Fully-Automated and Zero-Code LLM Agent Framework"
Minimal reproduction of DeepSeek R1-Zero