ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

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.

A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.

Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA

An Open-Source Asynchronous Coding Agent

AI agents running research on single-GPU nanochat training automatically

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

[ICLR 2026] Harder Is Better: Boosting Mathematical Reasoning via Difficulty-Aware GRPO and Multi-Aspect Question Reformulation

The absolute trainer to light up AI agents.

Implementation of "YaPO: Learnable Sparse Activation Steering Vectors for Domain Adaptation"

Implement a reasoning LLM in PyTorch from scratch, step by step

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Code for Bolmo: Byteifying the Next Generation of Language Models

A research project exploring fine-tuning BERT-style models for text generation

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

Optimize prompts, code, and more with AI-powered Reflective Text Evolution

adds Sequence Parallelism into LLaMA-Factory

ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation (NeurIPS 2025)

RL with Experience Replay

Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.

A Next-Generation Training Engine Built for Ultra-Large MoE Models