microsoft/WindowsAgentArena

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

56
/ 100
Established

This platform helps AI researchers and developers evaluate how well their multi-modal AI agents can perform tasks on a real Windows operating system. It takes your developed AI agents and a set of diverse Windows tasks as input, and outputs comprehensive benchmark results showing the agents' performance. Researchers and developers working on AI agentic workflows would find this tool valuable for rigorous testing.

833 stars.

Use this if you are an AI researcher or developer who needs to thoroughly test and benchmark the capabilities of your multi-modal AI agents in a realistic, scalable Windows environment.

Not ideal if you are an end-user looking for a pre-built AI agent to solve personal computing tasks.

AI-research agent-development performance-benchmarking operating-system-simulation AI-testing
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

833

Forks

92

Language

Python

License

MIT

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.