AI agent skills published by NVIDIA

The agent that grows with you

Claude Code Guide - Setup, Commands, workflows, agents, skills & tips-n-tricks go from beginner to power user!

Harness Engineering From Claude Code source code to AI Coding

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. 🫶

你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.

Make Any Website & Tool Your CLI. A universal CLI Hub and AI-native runtime. Transform any website, Electron app, or local binary into a standardized command-line interface. Built for AI Agents to …

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

Openclaw多智能体协同系统 | Multi-Agent OS for Decision Makers — 基于 OpenClaw (Clawbot) + Slack，让 AI 团队各司其职、自主稳定迭代。

NexRL is an ultra-loosely-coupled LLM post-training framework.

Browser automation CLI for AI agents

Secure, Fast, and Extensible Sandbox runtime for AI agents.

Public repository for Agent Skills

Train your AI self, amplify you, bridge the world

easy tinker-style RL-as-a-service demo

SkyRL: A Modular Full-stack RL Library for LLMs

Post-training with Tinker

Training API and CLI

Build, run, manage agentic software at scale.

Streamlit — A faster way to build and share data apps.

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

PyTorch-native post-training at scale

An interface library for RL post training with environments.

Our library for RL environments + evals

The absolute trainer to light up AI agents.

Democratizing Reinforcement Learning for LLMs

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

A version of verl to support diverse tool use

Kimi Code CLI is your next CLI agent.