Pinned Loading

1. CUA-RL-Environment-Ubuntu-24.04 CUA-RL-Environment-Ubuntu-24.04 Public

   CUA-RL-Environment: Customizable, GPU-accelerated (NVIDIA) RL environment for training computer-use AI agents in realistic isolated Ubuntu-Desktop Docker container with pre-installed browsers, IDEs…

   Dockerfile

2. the-eyes the-eyes Public

   The-Eyes is the visual cortex for Computer Use Agents, bridging desktops and AI. It abstracts OS capture to deliver high-fidelity streams to your backend. Build autonomous agents that "see" and int…

   Python

3. macos_actuation_control macos_actuation_control Public

   macOS Actuation CLI The macOS Actuation CLI is an intelligent middleware designed to enable AI agents (Computer Use Agents) to control containerized macOS reliably via SSH. It translates high-level…

   Python

4. windows_actuation_control windows_actuation_control Public

   Windows Actuation CLI is intelligent middleware enabling AI agents to reliably control containerized Windows via SSH. Utilizing a file-based command queue with AutoHotkey v2 watchers to bypass sess…

   Python

5. V1 V1 Public

   A video generation framework using HunyuanVideo and SVD for T2V, I2V, and V2V tasks with a Gradio interface.

   Python