Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation.
Rust agentai-agentapplecomputer-usecomputer-use-agentcontainerizationcuadesktop-automationhacktoberfestlumemacosmanusoperatorswiftvirtualizationvirtualization-frameworkwindowswindows-sandbox
added model compat
Dillon DuPont0f64e2eeef90
diff --git a/COMPATIBILITY.md b/COMPATIBILITY.mdindex 2ff8e5a6b4..a00d6e45b0 100644--- a/COMPATIBILITY.md+++ b/COMPATIBILITY.md@@ -6,7 +6,7 @@- [Ubuntu/Linux Host](#ubuntulinux-host)- [Windows Host](#windows-host)- [VM Emulation Support](#vm-emulation-support)-- [Installation Method Details](#installation-method-details)+- [Model Provider Compatibility](#model-provider-compatibility)---@@ -71,49 +71,16 @@| **Cloud** | π§ Coming soon | β Full support | π§ Coming soon | Currently Ubuntu only, macOS/Windows in development || **Winsandbox** | β Not supported | β Not supported | β Windows only | Windows Sandbox environments only |-### VM Emulation Details--#### Lume VM Support-- **macOS VMs**: β Full native support with official images-- **Ubuntu/Linux VMs**: β οΈ Limited support - requires custom image creation-- **Windows VMs**: β οΈ Limited support - requires custom image creation--#### Cloud VM Support-- **Ubuntu/Linux VMs**: β Full support with managed cloud instances-- **macOS VMs**: π§ Coming soon - in development-- **Windows VMs**: π§ Coming soon - in development--#### Windows Sandbox VM Support-- **Windows VMs**: β Full support for Windows Sandbox environments-- **macOS/Linux VMs**: β Not supported - Windows Sandbox only runs Windows-----## Installation Method Details--### playground-docker.sh-- **Containerized setup** using Docker-- Handles all dependencies automatically-- Requires Docker Desktop (Windows/macOS) or Docker Engine (Linux)-- **Windows note**: Must run in WSL2 environment--### Dev Container-- **Development-focused** setup for contributors-- Integrates with VS Code and WindSurf IDEs-- Provides consistent development environment-- **Windows note**: Requires WSL2 backend for Docker--### PyPI packages-- **Manual installation** via pip-- Most flexible installation method-- Allows custom configurations and integrations-- **Windows note**: Shell scripts require WSL2, but Python packages work natively-----+## Model Provider Compatibility-## Legend+*This section shows which **AI model providers** are supported on each host operating system.*-- β **Full support**: All features work natively without limitations-- β οΈ **Partial support**: Requires additional setup (e.g., WSL2) or has limitations-- β **Not supported**: Feature/provider combination is not available-- π§ **Coming soon**: Feature/provider combination is in development+| Provider | macOS Host | Ubuntu/Linux Host | Windows Host | Notes |+|----------|------------|-------------------|--------------|-------|+| **Anthropic** | β Full support | β Full support | β Full support | Cloud-based API |+| **OpenAI** | β Full support | β Full support | β Full support | Cloud-based API |+| **Ollama** | β Full support | β Full support | β Full support | Local model serving |+| **OpenAI Compatible** | β Full support | β Full support | β Full support | Any OpenAI-compatible API endpoint |+| **MLX VLM** | β macOS only | β Not supported | β Not supported | Apple Silicon required. PyPI installation only. |\ No newline at end of filediff --git a/README.md b/README.mdindex fa4c2282de..8caac3834f 100644--- a/README.md+++ b/README.md@@ -81,6 +81,19 @@ This repository includes a [Dev Container](./.devcontainer/README.md) configurat---+### Option 3: PyPI+*Direct Python package installation*++```bash+# conda create -yn cua python==3.12++pip install -U "cua-computer[all]" "cua-agent[all]"+python -m agent.ui # Start the agent UI+```++Or check out the [Usage Guide](#-usage-guide) to learn how to use our Python SDK in your own code.++---## Supported [Agent Loops](https://github.com/trycua/cua/blob/main/libs/agent/README.md#agent-loops)- [UITARS-1.5](https://github.com/trycua/cua/blob/main/libs/agent/README.md#agent-loops) - Run locally on Apple Silicon with MLX, or use cloud providers@@ -88,16 +101,16 @@ This repository includes a [Dev Container](./.devcontainer/README.md) configurat- [Anthropic CUA](https://github.com/trycua/cua/blob/main/libs/agent/README.md#agent-loops) - Use Anthropic's Computer-Use capabilities- [OmniParser-v2.0](https://github.com/trycua/cua/blob/main/libs/agent/README.md#agent-loops) - Control UI with [Set-of-Marks prompting](https://som-gpt4v.github.io/) using any vision model-## π₯οΈ OS Compatibility+## π₯οΈ Compatibility-For detailed compatibility information including host OS support and VM emulation capabilities, see the [**Compatibility Matrix**](./COMPATIBILITY.md).+For detailed compatibility information including host OS support, VM emulation capabilities, and model provider compatibility, see the [Compatibility Matrix](./COMPATIBILITY.md).<br/><br/>-# π» Developer Guide+# π Usage Guide-Follow these steps to use C/ua in your own code. See [Developer Guide](./docs/Developer-Guide.md) for building from source.+Follow these steps to use C/ua in your own Python code. See [Developer Guide](./docs/Developer-Guide.md) for building from source.### Step 1: Install Lume CLI