AI Agent Skills for Wan — Enable your AI Agent to easily leverage Wan's AIGC capabilities.

verl: Volcano Engine Reinforcement Learning for LLMs

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…

Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.

MUA-RL: MULTI-TURN USER-INTERACTING AGENT REINFORCEMENT LEARNING FOR AGENTIC TOOL USE

🙌 OpenHands: AI-Driven Development

A growing set of skills to polish interfaces built by agents.

Claude Code skill that removes signs of AI-generated writing from text

NanoBanana PPT Skills 基于 AI 自动生成高质量 PPT 图片和视频的强大工具，支持智能转场和交互式播放

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require e…

"🐈 nanobot: The Ultra-Lightweight Personal AI Assistant"

Your 24/7 all-scenario AI agent that gets work done for you.

The best free and open-source automated time tracker. Cross-platform, extensible, privacy-focused.

An open-source vibe coding platform that helps you build your own vibe-coding platform, built entirely on Cloudflare stack

Multi-agent pipeline coordination: Linear, DAG, and Debate modes for AI agent orchestration

Baidu Map MCP Server

Official implementation of EgoX EgoPrior Renderer: Generate ego-view videos from exo-view input using ViPE-based 3D reconstruction and point cloud rendering

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"

Official Pytorch implementation for "EgoWorld: Translating Exocentric View to Egocentric View using Rich Exocentric Observations" (ICLR 2026)

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Codes for the ICCV 2025 paper: "Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery"

An open-source alternative to Claude Cowork built for teams, powered by opencode

Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation [Siggraph Asian 2025]