Synthetic data generation, post-training, and E2B benchmark evaluation infrastructure.

The RedStone repository includes code for preparing extensive datasets used in training large language models.

This repository contains the code for https://decimer.ai

AI agents running research on single-GPU nanochat training automatically

Get your documents ready for gen AI

Data Efficacy for Language Model Training

The batteries-included agent harness.

Building and Scaling RL environments in the age of LLMs

An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms

The agent that grows with you

将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

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

Site-backed dataset, reconciled package files, and interactive docs for OpenAI vs Anthropic compute estimates.

Official PyTorch implementation for "Large Language Diffusion Models"

from vibe coding to agentic engineering - practice makes codex perfect

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

An agentic skills framework & software development methodology that works.

Universal scraping tool, which allows you to extract data using multiple environments

你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

Measuring and evolving with the frontier of agent work

OpenClaw-RL: Train any agent simply by talking

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

Language models scale reliably with over-training and on downstream tasks

maximal update parametrization (µP)

🚀 Efficient implementations for emerging model architectures

Our code for ICLR'25 paper "DataMan: Data Manager for Pre-training Large Language Models".