Stars
A Claude Code skill that turns any codebase into a beautiful, interactive single-page HTML course for non-technical vibe coders.
An open-source AI agent that lives in your terminal.
SWE-bench: Can Language Models Resolve Real-world Github Issues?
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
Claude reads its own source code — 17-chapter architectural deep-dive into Claude Code v2.1.88. EN/ZH bilingual.
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.
This is the official implementation of Multi-Agent PPO (MAPPO).
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically ground…
Efficient, Python-native, end-to-end MoE training in ~10K lines of code.
Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.
cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals
VMAS is a vectorized differentiable simulator designed for efficient Multi-Agent Reinforcement Learning benchmarking. It is comprised of a vectorized 2D physics engine written in PyTorch and a set …
An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Autonomous GPU Kernel Generation & Optimization via Deep Agents
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…
AI agents running research on single-GPU nanochat training automatically
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A lightweight, AI-native training framework for large language models. Designed for fast iteration, reproducible experiments, and modular configuration across SFT, RLVR, and evaluation workflows.
An agent for CUDA compute-communication kernel co-design
Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs
Helios: Real Real-Time Long Video Generation Model
Utility scripts for PyTorch (e.g. Make Perfetto show some disappearing kernels, Memory profiler that understands more low-level allocations such as NCCL, ...)
A lightweight inference engine supporting speculative speculative decoding (SSD).