Commit Graph

1352 Commits

Author SHA1 Message Date
Subash Shibu
3167339e45 Add hosted GBOX agent for OSWorld evaluation (#376) 2025-11-13 13:13:31 +08:00
Pengxiang-Li
00b6468eb7 feat/dart_gui (#371) 2025-11-07 21:50:01 +08:00
yiqilin
6d43dbc532 Update GIMP evaluation examples to replace local file paths with cloud file URLs for consistency and accessibility. (#372) 2025-11-07 21:49:49 +08:00
Timothyxxx
8365edc975 Add new section in README for OSWorld-MCP project 2025-10-30 06:06:48 +00:00
Daphne Barretto
21c2b7629b Add consistent scores validation (#368)
* Add consistent scores validation

* revert osworld_run_maestro.py changes
2025-10-29 01:44:48 +08:00
Timothyxxx
3bf54c92a9 Merge branch 'main' of github.com:xlang-ai/OSWorld 2025-10-23 14:28:14 +08:00
Timothyxxx
a484f2e484 Update setup.py for version bump and dependency adjustments
- Bump version from 1.0.0 to 1.0.1
- Update numpy dependency to allow versions >=1.26 and <3
- Adjust pandas dependency to allow versions >=2.2 and <2.3
- Add new __init__.py file in the docker provider directory
2025-10-23 14:27:52 +08:00
Atharva Gundawar
9f97535ef9 oswrold agent wrapper for trained v7 (#360) 2025-10-18 02:29:15 +08:00
ludunjie.ldj
afd29115da support aliyun eval of qwen3vl 2025-10-16 16:20:54 +08:00
Dunjie Lu
55372c4432 Fix API base URLs for OpenAI and DashScope
Updated the base URLs for OpenAI and DashScope API calls.
2025-10-14 12:57:00 +08:00
Dunjie Lu
d25464c203 Djlu/qwen3vl dash (#356)
* support dashscopoe sdk to call qwen3-vl-plus

* support dashscopoe sdk to call qwen3-vl-plus

---------

Co-authored-by: Timothyxxx <Timothyxxx@users.noreply.github.com>
2025-10-13 16:31:06 +08:00
Xinyuan Wang
f9e9273b3b OpenCUA-72B (#354)
* use aws pub ip

* os task fix: set the default dim screen time to be 300s

* OpenCUA-72B

* update password

* update

* update

* update opencua72b agent

* change provider ip

---------

Co-authored-by: Jiaqi <dengjiaqi@moonshot.cn>
2025-10-13 10:39:33 +08:00
Yan98
ddb8372a6c init public release (#350) 2025-10-06 22:16:31 +08:00
eun2ce
5eff00a9e3 Fix #347: Fix NameError in open_file timeout message (#351)
- Fix undefined 'timeout' variable in error message
- Use defined TIMEOUT constant instead of undefined timeout variable
- Prevents NameError when LibreOffice crashes during file opening
2025-10-06 22:14:15 +08:00
Timothyxxx
ff6285cfbb Add safe browsing feature to Chrome evaluator
- Implemented `get_enable_safe_browsing` function to retrieve safe browsing settings based on the operating system.
- Updated the `__init__.py` to include the new function.
- Modified JSON examples to reflect the change from enabling enhanced safety browsing to enabling safe browsing.
- Added necessary commands in the JSON examples for setting up preferences for safe browsing.
2025-10-05 04:56:08 +00:00
Danyang Zhang
afd5952e44 ver Oct3rd (#349)
updated a series of instructions to ask the agent not to do any
unnecessary actions.
2025-10-04 00:13:29 +08:00
Timothyxxx
1572068035 Refactor evaluator functions in JSON examples to use URL pattern matching. Update expected URL formats to regex patterns for better validation in chrome evaluation examples. 2025-10-01 19:20:06 +00:00
Timothyxxx
9be518435c Update GIMP evaluation examples to replace local file paths with cloud file URLs for consistency and accessibility. 2025-10-01 09:54:52 +00:00
Timothyxxx
bfb467da18 Merge branch 'main' of github.com:xlang-ai/OSWorld 2025-10-01 06:56:43 +00:00
Timothyxxx
4c685bed99 Update run_maestro.py to run in headless mode with a single environment and specify result directory. Adjust default TTL for AWS instances from 60 to 180 minutes in config.py. Enhance AWSProvider to handle missing security groups, subnet IDs, and instance types with fallbacks, and improve termination logic to skip already terminated instances while logging relevant information. 2025-10-01 06:56:33 +00:00
eun2ce
5eb5417188 fix #210: add a11y_tree support to UITARSAgent (#346) 2025-09-26 18:25:28 +08:00
Yanxiao Zhao
6827949418 fix _update_browse_history_setup (#345) 2025-09-25 13:22:40 +08:00
Yanxiao Zhao
a4f8fe2f00 Add autoglm-os-9b-v (#344)
* update for autoglm-v

* Update run_autoglm.py

---------

Co-authored-by: hanyullai <hanyullai@outlook.com>
2025-09-24 19:43:28 +08:00
alexandruilie7
f59cf00cae Add ui agent (#343)
* add uipath agent

* readme update
2025-09-24 19:42:46 +08:00
Long Chen
088e68798c update aworldguiAgent code (#342) 2025-09-23 16:50:29 +08:00
Timothyxxx
584c7a9875 Enhance AWSProvider instance handling with fallback mechanisms for security groups, subnet IDs, and instance types. Implement checks to skip termination of instances already in 'shutting-down' or 'terminated' states, and handle potential termination errors gracefully. 2025-09-18 07:16:10 +00:00
molanhand
7213eca069 support mano agent (#338)
Co-authored-by: Fei Hu <molanhand@users.noreply.github.com>
2025-09-16 18:10:29 +08:00
ZhangZuhao
dc7e46e7aa Refactor platform detection for VM image download (#337)
Sometimes the platform detection for VM image download is wrong
2025-09-15 21:00:15 +08:00
Dunjie Lu
b012301609 support qwen3vl agent (#336)
Co-authored-by: root <ludunjie1219@github.com>
2025-09-15 16:04:29 +08:00
Hiroid
a668670349 fix(maestro): Fixed the debug logging level (#334)
Co-authored-by: Liangxuan Guo <guoliangxuan@deepmatrix.com.cn>
2025-09-11 01:03:59 +08:00
Hiroid
3a4b67304f Add multiple new modules and tools to enhance the functionality and extensibility of the Maestro project (#333)
* Added a **pyproject.toml** file to define project metadata and dependencies.
* Added **run\_maestro.py** and **osworld\_run\_maestro.py** to provide the main execution logic.
* Introduced multiple new modules, including **Evaluator**, **Controller**, **Manager**, and **Sub-Worker**, supporting task planning, state management, and data analysis.
* Added a **tools module** containing utility functions and tool configurations to improve code reusability.
* Updated the **README** and documentation with usage examples and module descriptions.

These changes lay the foundation for expanding the Maestro project’s functionality and improving the user experience.

Co-authored-by: Hiroid <guoliangxuan@deepmatrix.com>
2025-09-08 16:07:21 +09:00
Timothyxxx
029885e78c Merge branch 'main' of github.com:xlang-ai/OSWorld 2025-09-05 15:36:39 +00:00
Timothyxxx
640f3fcd96 Update default path_to_vm argument to None in quickstart.py for improved flexibility 2025-09-05 15:36:31 +00:00
Timothyxxx
756923beea Update instruction wording in LibreOffice Impress example to clarify text color change requirements. Address https://github.com/xlang-ai/OSWorld/issues/324 2025-09-01 23:29:47 +08:00
Timothyxxx
0c681b91e0 Fix README update 2025-09-01 15:15:50 +00:00
aneeshprasad1
8513e8c89e Add quickstart script and update README (#325)
Co-authored-by: Aneesh Prasad <aneeshprasad@Aneeshs-MacBook-Pro.local>
2025-09-01 23:14:24 +08:00
Howie
756e006af6 add support for mobile agent v3 (#328)
* add support for mobile agent v3

* add mobile_agent

* add support for mobile agent v3
2025-08-31 22:58:41 +08:00
hanyullai
54a14cbc07 fix multienv bug (#327) 2025-08-30 11:10:53 +08:00
Howie
3344abd641 Add support for GUI-Owl agent (#318)
* add run_multienv_owl.py

* add owl_agent.py
2025-08-27 18:03:39 +08:00
Timothyxxx
ef2f35de22 Add resource group ID support for Aliyun VM allocation
- Introduced ALIYUN_RESOURCE_GROUP_ID environment variable to manage resource group assignments during VM allocation.
- Updated the _allocate_vm function to include resource group ID in the request if specified.
- Modified VNC URL logging to use public IP when available, enhancing clarity in access information.
- Maintained existing code logic while improving functionality for resource management and logging.
2025-08-26 13:28:23 +08:00
Timothyxxx
4c773f6f7c Merge branch 'main' of github.com:xlang-ai/OSWorld 2025-08-22 23:29:21 +08:00
Timothyxxx
ebda4d8b3f Add Aliyun SDK dependencies and implement TTL configuration for ECS instances
- Added new dependencies for Aliyun ECS SDK in requirements.txt and setup.py to support instance management features.
- Introduced a new config module to handle TTL settings for ECS instances, allowing for auto-termination based on environment variables.
- Updated the manager to utilize TTL settings, including scheduling instance termination with proper error handling and logging.
- Maintained existing code logic while enhancing functionality for improved instance lifecycle management.
2025-08-22 23:28:58 +08:00
Timothyxxx
15d9ddb612 update coact: add autogen/cache 2025-08-21 19:03:35 +00:00
Timothyxxx
b14f1c7345 Merge branch 'main' of github.com:xlang-ai/OSWorld 2025-08-21 09:38:37 +00:00
Timothyxxx
ead564c92b Update dependencies and refactor DesktopEnv initialization
- Removed specific versioning for the 'requests' library in requirements.txt and setup.py to allow for more flexible updates.
- Refactored the DesktopEnv class to streamline the emulator initialization process, enhancing error handling and logging during startup.
- Improved retry logic for file uploads in SetupController, ensuring robust handling of network issues and providing clearer error messages.
- Maintained existing code logic while enhancing clarity and reliability in the DesktopEnv and SetupController classes.
2025-08-21 09:38:28 +00:00
Timothyxxx
b3e1c0344d Update OpenCV dependency to headless version in requirements and setup files
- Replaced 'opencv-python' with 'opencv-python-headless' in both requirements.txt and setup.py to reduce unnecessary GUI dependencies.
- Added a new .gitkeep file in the logs directory to ensure it is tracked in version control.
- Maintained existing code logic while improving dependency management.
2025-08-20 01:26:24 +08:00
Timothyxxx
492c910e94 Refactor AWS scheduler role handling in scheduler_utils.py
- Improved error handling and logging for role resolution and creation.
- Added checks to ensure the trust policy allows for AWS EventBridge Scheduler to assume the role.
- Implemented retry logic for scheduling EC2 termination to handle IAM eventual consistency.
- Maintained existing code logic while enhancing robustness and clarity in role management.
2025-08-18 17:57:31 +00:00
Timothyxxx
3a96fd5046 Add TTL configuration for AWS instance management
- Introduced a new config module to manage TTL settings for EC2 instances, allowing for auto-termination based on environment variables.
- Updated the AWSProvider and manager to utilize the new TTL settings, including scheduling instance termination via EventBridge Scheduler.
- Added utility functions for resolving the scheduler role ARN and creating termination schedules, ensuring robust error handling and logging.
- Maintained existing code logic while integrating new features for improved instance lifecycle management.
2025-08-18 17:30:49 +00:00
Adam Yanxiao Zhao
75f00fea62 Fix AutoGLM-OS custom env reset func (#312)
* Add AWS config for autoglm-os agent script

* update default password

* fix autoglm-os reset
2025-08-18 18:12:09 +08:00
Timothyxxx
a5dc64c943 Update Aliyun guidelines to include SSH and VNC password setup script 2025-08-18 07:24:39 +00:00