TradingAgents: Multi-Agents LLM Financial Trading Framework

A Lightweight LLM Post-Training Library

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Nano vLLM

Skills for Real Engineers. Straight from my .claude directory.

A tool that locates, downloads, and extracts machine translation corpora

A project implementing various agentic RL based on the Slime post-training framework

slime is an LLM post-training framework for RL Scaling.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Create beautiful slides on the web using Claude's frontend skills

A high-throughput and memory-efficient inference and serving engine for LLMs

You like pytorch? You like micrograd? You love tinygrad! ❤️

Mailing list style code reviews for github

Minimal yet performant LLM examples in pure JAX

The best ChatGPT that $100 can buy.

The missing tiktoken training code

Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.

get things from one computer to another, safely

Sutskever 30 implementations inspired by https://papercode.vercel.app/

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

verl: Volcano Engine Reinforcement Learning for LLMs

Learn GCP (Google Cloud Platform) from scratch. Learn through video tutorials, notes and architecture diagrams.

🤖 My comprehensive learning journey through OpenAI Agents SDK - from basics to production-ready applications. Learning by teaching, building by doing. Inspired by expert educational resources, enha…