A straightforward method for training your LLM, from downloading data to generating text.

PyTorch native post-training library

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

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

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

100+ AI Agent & RAG apps you can actually run — clone, customize, ship.

Build, run, and manage agent platforms.

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, an…

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command li…

Claude Code skill that transforms vague prompts into structured, expert-level prompts using 7 research-backed frameworks (CO-STAR, RISEN, RISE, TIDD-EC, RTF, CoT, CoD)

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

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

[ICML 2026] NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

Tools for merging pretrained large language models.

A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention

"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"

Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.

AI agents running research on single-GPU nanochat training automatically