Lightweight coding agent that runs in your terminal

DeepSeek Harness: Everything is a Plugin.

Qwen-CUA: Native Computer Use for (Almost) Everything — a screenshot-driven agent that operates computers with keyboard and mouse, jointly developed by the Qwen Team and XLang Lab.

Make any agent harness multimodal-native.

The unified framework for sim & real robot teleoperation

Open Frontier Intelligence

Open-source framework for computer use agents: VeriGen verifiable task synthesis, online RL training (AgentRL), and OSWorld/ScienceBoard evaluation.

MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training

OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks

Qwen-AgentWorld: Language World Models for General Agents

Post-training with Tinker

Official repository for the survey "Reinforcement Learning for Visual Generation: A Model-Oriented Survey".

HY-Embodied-0.5-X: An Enhanced Embodied Foundation Model for Real-World Agents

GUI Agent for E2E Testing

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

Multimodal RL training framework for diffusion & omni models

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

JoyAI-VL-Interaction: An Open Real-time Video-Language Interaction System

Reference code for the articraft paper.

[ECCV 2026] Generative Refinement Networks for Visual Synthesis (Support C2I & T2I & T2V)

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

MiMo Code: Where Models and Agents Co-Evolve

Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?

GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing