Stars
Domain-agnostic multi-agent software design and evolution harness
Cookiy AI Skill for AI agents (Claude, Codex, Cursor, OpenClaw) — end-to-end user research: AI interviews, synthetic users, quant surveys, participant recruitment.
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
AI-Driven Scientific and Algorithmic Discovery
from vibe coding to agentic engineering - practice makes claude perfect
Huashu Design · HTML-native design skill for Claude Code · Claude Code 里 HTML 原生的设计 skill · 高保真原型 / 幻灯片 / 动画 + 20 设计哲学 + 5 维评审 + MP4 导出 · Agent-agnostic
CADAM is the open source text-to-CAD web application
A 15TB Collection of Physics Simulation Datasets
OpenClaw-RL: Train any agent simply by talking
AI agents running research on single-GPU nanochat training automatically
A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物
Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI.
This repo powers my experiment where ChatGPT manages a real-money micro-cap stock portfolio.
OpenTinker is an RL-as-a-Service infrastructure for foundation models
Video+code lecture on building nanoGPT from scratch
Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.
A Python library for inference-time scaling LLMs
Build effective agents using Model Context Protocol and simple workflow patterns
[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)
Simple and efficient DeepSeek V3 SFT using pipeline parallel and expert parallel, with both FP8 and BF16 trainings
A comprehensive social media management tool designed to help you create, format, and post content across multiple platforms including LinkedIn, Twitter/X, Bluesky, and Mastodon. Features advanced …
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Synthetic Data Generation Toolkit for LLMs
Recipes to scale inference-time compute of open models
Get your documents ready for gen AI
Docling core data types and transformations
InstructLab Core package. Use this to chat with a model and execute the InstructLab workflow to train a model using custom taxonomy data.
A topic-centric list of HQ open datasets.