cua
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
Learn how to contribute custom environment adapters to the Cua-Bench registry. Implement an EnvironmentAdapter class, define task metadata, generate the registry, and submit a pull request.
How Cua Handles Screen State Verification and Element Detection for Reliable AutomationLearn how Cua achieves reliable automation by combining AI screenshot validation with dual-path element discovery using accessibility trees and computer vision OCR.
How to Implement Rate Limiting and Cost Controls for LLM API Calls in CuaImplement LLM API rate limiting and cost controls in Cua. Learn to use exponential backoff retries and BudgetManagerCallback for budget management and agent execution stops.
How to Scale Cua Agents Across Multiple Cloud VMs: Async Fleet Management GuideScale Cua agents across multiple cloud VMs efficiently. Learn how to use VMProviderType.CLOUD and asyncio.Semaphore for concurrent agent execution while managing API limits and resources.
How Cua's MCP Server Session Management Works for Long-Running Agent TasksDiscover how Cua's MCP server uses session management and idle detection to efficiently handle long-running agent tasks without resource waste.
How to Export Agent Trajectories for Training Reinforcement Learning Models in CuaExport Cua agent trajectories for RL training using the CLI or zip_trajectory() function. Streamline your reinforcement learning pipelines with this essential data format. Learn how now.
cua-computer vs cua-computer-server: Understanding the Client-Server ArchitectureLearn the difference between cua-computer client SDK and cua-computer-server. Understand how this client-server architecture enables remote execution and sandbox management.
How Cua Handles Multi-Touch Gestures and Mobile-Specific InteractionsDiscover how Cua handles multi-touch gestures and mobile interactions with its transport-agnostic architecture and high-level async API. Supports ADB and gRPC.
How to Create a Custom Skill for CuaBot to Automate Specific GUI TasksLearn to create a custom skill for CuaBot to automate GUI tasks. Follow our guide or use the CLI to record and train your unique automation workflows.
Security Model for Running Untrusted Agent Code in Cua SandboxesDiscover the Cua security model for running untrusted agent code. Learn how Cua uses sandboxing with process isolation, privilege restriction, and network sandboxing for robust defense.
How to Debug Cua Agent Failures Using Telemetry and Tracing: A Complete GuideDebug Cua agent failures effectively. Learn to enable telemetry and tracing for detailed crash analytics, session logs, screenshots, and API call sequences to pinpoint and resolve issues.
How Lume Uses Apple's Virtualization Framework for Near-Native macOS PerformanceDiscover how Lume uses Apple's Virtualization Framework to achieve near-native macOS performance on Apple Silicon. Run macOS VMs directly with hardware acceleration and paravirtualized I/O.
Have a question about this repo?
These articles cover the highlights, but your codebase questions are specific. Give your agent direct access to the source. Share this with your agent to get started:
curl -s "https://instagit.com/install.md" 
Maintain an open-source project? Get it listed too →