CUA

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider, using Stream's edge network for ultra-low latency realtime interactions.

开源的计算机使用 Agent 框架，像人类一样操作图形界面完成复杂任务，支持自主学习和经验积累。

AI 驱动的本地自动化助手，类似 Manus 的电脑使用 Agent，通过自然语言让电脑自动工作。

Open-source deep research agent from Alibaba Tongyi Lab, using multi-stage iterative information retrieval and reasoning to conduct deep analysis, synthesis, and summarization of complex topics with web search and document analysis.