OpenCUA

A research prototype of a human-centered web agent from Microsoft Research, emphasizing human-in-the-loop interaction for collaborative web browsing and data collection tasks.

An adaptive web scraping framework that intelligently handles anti-bot measures, from single requests to full-scale crawls, designed for AI agent data collection.

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.

Open-sourced computer use agents that can operate on cross-platform environments including Windows, macOS, Ubuntu, and Android. ICLR 2026 Oral paper project.