Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.

Official implementation of VLAA-GUI series

A Universal Platform for Training and Evaluation of Mobile Interaction

Mobile-Bench: An Evaluation Benchmark for LLM-based Mobile Agents

[NeurIPS 2025 Spotlight] OpenCUA: Open Foundations for Computer-Use Agents

Out-of-the-box (OOTB) GUI Agent for Windows and macOS

The official repository of Qwen-VLA

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

Ideogram 4: Open image model at the forefront of design

A cross-platform GUI automation Python module for human beings. Used to programmatically control the mouse & keyboard.

Native and Compact Structured Latents for 3D Generation

Benchmarking Agentic Procedural 3D Modeling Via Code

[CVPR 2026] VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving

Code for "Improving Robotic Manipulation with Efficient Geometry-Aware Vision Encoder"

A Minimal and Elegant Framework & Tutorial for Real-Time Interactive World Models

A curated collection of resources, tools, and frameworks for developing GUI Agents.

Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos (ICML 2026)

OpenMMLab Pre-training Toolbox and Benchmark

Scalable pipeline for synthesizing verifiable RLVR training data for computer-use agents