xlang-ai / OSWorld
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Why this job: matched by what the repo talks about: benchmark, open, task, agent
What it does
Suppose you are operating on a system that has not been virtualized (e.g. your desktop, laptop, bare metal machine), meaning you are not utilizing a virtualized environment like AWS, Azure, or k8s. If this is the case, proceed with the instructions below. However, if you are on a virtualized platform, please refer to the Docker section.
Get started
pip install desktop-env- Maintenance
- Active
- Last commit 8 days ago
- Stars
- 3,257
- +8 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.1.16
- Released 2 years ago
- Built with
- Python
- 99% of the code
Is it looked after?
- Contributors
- 7
- Last 90 days
- Issues
- 40% closed
- 151 still open
- Pull requests
- 357 merged
- 22 waiting
- Releases
- 2
- 0 in the last year
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| TsinghuaC3I / MedXpertQA | 185 | 2 months ago | MIT | No downloads |
| StarTrail-org / DRPixel | 43 | 8 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 99%
- JavaScript <1%
- CSS <1%
- Shell <1%
Topics
- agent
- artificial-intelligence
- benchmark
- multimodal
- reinforcement-learning
- rpa
- code-generation
- language-model
- cli
- gui
- natural-language-processing
- large-action-model
Project record
- JobEvals and observability
- StatusListed
- Commits1,668
- Forks558
- Watching30
- Stars in 28 days+55
- CreatedOct 16, 2023
- First seen by usNov 7, 2026
- CheckedNov 10, 2026