Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.
active 2025-02-07 → 2026-04-23 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 441 days from 2025-02-07 to 2026-04-23. Pushes: 0 total, peak 0 in a day. Pull requests: 2 total, peak 2 in a day. Issues: 12 total, peak 2 in a day. Comments: 9 total, peak 1 in a day. Stars: 124 total, peak 3 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| KwongFuk | 4 | 0 | 0 | 2 |
| alckasoc | 3 | 0 | 0 | 1 |
| heroding77 | 2 | 0 | 0 | 1 |
| JYL67 | 1 | 0 | 0 | 0 |
| sharryXR | 1 | 0 | 0 | 0 |
| abrichr | 1 | 0 | 0 | 0 |
| yuh-yang | 1 | 0 | 0 | 1 |
| zqpresent | 1 | 0 | 0 | 1 |
| dahaobenhao | 1 | 0 | 0 | 0 |
| jianghuyihei | 1 | 0 | 0 | 0 |
| dependabot[bot] | 1 | 0 | 0 | 1 |
| PaulJiangMS | 1 | 0 | 1 | 0 |
| weiyuanyue | 1 | 0 | 1 | 0 |
| axiomaster | 1 | 0 | 0 | 0 |
| shiqian-su | 1 | 0 | 0 | 1 |
| Occi-Dental-Mask | 1 | 0 | 0 | 0 |
| microsoft-github-policy-service[bot] | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue comment#80dependabot[bot]2026-04-13 19:58Bump pillow from 10.3.0 to 12.1.1 in /src/win-arena-container/vm/setup/server
- Issue#79abrichr2026-01-29 01:29Navi agent generates incorrect method signature for computer.mouse.drag() causing 500 errors
- Issue#77sharryXR2025-09-24 11:44Whether the current project supports the development of tasks related to new applications
- Issue#76jianghuyihei2025-09-23 11:43Can I run this container on a Mac?
- Issue comment#75yuh-yang2025-09-22 23:21Network issue during evaluation
- Issue#75Occi-Dental-Mask2025-08-17 08:14Network issue during evaluation
- Issue#74axiomaster2025-08-12 16:44In the paper on arXiv, Table 7 only lists 146 tasks, with 8 tasks missing from the "Windows System" domain.
- Issue comment#73microsoft-github-policy-service[bot]2025-07-30 07:41Test01
- Issue#72dahaobenhao2025-07-28 13:29winarena Docker container stuck at "waiting for response" during graceful termination
- Issue comment#69KwongFuk2025-07-28 06:37Stay on this screen while running the test
- Issue#69KwongFuk2025-07-28 06:37Stay on this screen while running the test
- Issue comment#69dahaobenhao2025-07-25 04:30Stay on this screen while running the test
- Issue#70jtrecok2025-07-19 22:34Still being maintained?
- Issue comment#68heroding772025-06-21 08:32No Excel App to Open Excel File
- Issue#68heroding772025-05-11 05:02No Excel App to Open Excel File
- Issue comment#37zqpresent2025-04-29 04:03Connection Timeout Error on run.py Script when Executing Task File
- Issue comment#59shiqian-su2025-04-26 15:17Can't build local image
- Issue#65JYL672025-04-10 05:44problem while preparing the image
- Issue comment#64alckasoc2025-03-21 00:00Azure ML Compute Instance: azure.core.exceptions.HttpResponseError: Operation returned an invalid status 'A name for an Azure ML Compute Instance must be between 3 and 24 characters in length...
- Issue#64alckasoc2025-03-21 00:00Azure ML Compute Instance: azure.core.exceptions.HttpResponseError: Operation returned an invalid status 'A name for an Azure ML Compute Instance must be between 3 and 24 characters in length...
- Issue#64alckasoc2025-03-20 23:54Azure ML Compute Instance: azure.core.exceptions.HttpResponseError: Operation returned an invalid status 'A name for an Azure ML Compute Instance must be between 3 and 24 characters in length...
- Pull request#56weiyuanyue2025-02-21 05:51
- Pull request#60PaulJiangMS2025-02-21 05:45
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 124 stars here means stars gained during the window, not the repo's star count.