microsoft/WindowsAgentArena
Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.
Provides isolated Windows 11 VM environments with desktop automation capabilities (mouse, keyboard, screenshots) wrapped in Docker containers, enabling agents to interact with real OS applications and UI elements. Integrates with OpenAI/Azure LLM endpoints and features a built-in Omniparser screen understanding model for visual grounding. Supports both local deployment via Docker/WSL and large-scale distributed execution across Azure ML infrastructure for rapid multi-task benchmarking.
833 stars.
Stars
833
Forks
92
Language
Python
License
MIT
Category
Last pushed
Feb 11, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/microsoft/WindowsAgentArena"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Related agents
StonyBrookNLP/appworld
🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and...
qualifire-dev/rogue
AI Agent Evaluator & Red Team Platform
future-agi/ai-evaluation
Evaluation Framework for all your AI related Workflows
agentscope-ai/OpenJudge
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
dreadnode/AIRTBench-Code
Code Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models