Official implementation of "SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience"
-
Updated
Aug 7, 2025 - Python
#
osworld
Here are 5 public repositories matching this topic...
[NeurIPS 2025] Official repository of RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents
-
Updated
Dec 2, 2025 - HTML
Mano-P: Open-source GUI-VLA agent for edge devices. #1 on OSWorld (specialized, 58.2%). Runs locally on Apple M4 Mac mini/MacBook — no data leaves your device.Mano-P 是一个开源 GUI-VLA 项目，支持在 Mac mini/MacBook 上或通过算力棒本地运行推理，实现纯视觉驱动的跨平台 GUI 自动化操作。数据完全本地处理，支持复杂多步骤任务规划与执行。
desktop-automation mano gui-automation edge-computing on-device-ai local-inference vision-language-action multimodal-ai gui-grounding osworld computer-use-agents visual-language-model mano-p
-
Updated
Mar 26, 2026
Edge-optimized OpenCUA-7B computer-use agent evaluated on OSWorld, exploring systematic vLLM inference optimizations across CPU and GPU, including precision tuning, image history management, speculative decoding, and prefix caching.
quantization agents multimodal inference-optimization edge-ai vllm speculative-decoding gui-agents prefix-caching osworld opencua
-
Updated
Dec 18, 2025 - Python
Evaluation of GPT-4o-mini on OSWorld desktop automation benchmark. Compares screenshot-only vs accessibility tree-enhanced approaches across 10 tasks (Chrome, LibreOffice, file ops, etc). Documents critical coordinate extraction failures and provides architectural recommendations for GUI agents.
-
Updated
Nov 20, 2025 - Python
Improve this page
Add a description, image, and links to the osworld topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the osworld topic, visit your repo's landing page and select "manage topics."