Join our Discord
Home
Local workspace on Ubuntu 24.04
cua-sandbox
eval-runs
screenshots
datasets
README.md2 KB
run_eval.sh4 KB
episode-042.json18 KB
Scale computer fleets
for every
Run training, eval, and data-generation workloads in parallel on Linux, Windows, macOS, and Android machines. Fork from snapshots, reproduce failures, and turn agent activity into training data.
Cua Driver integrations
Why Cua
Where generic GUI sandboxes stop.
01
Background drivers for Computer-Use
Send clicks and keystrokes to a chosen desktop window without moving the system cursor.
02
Cross-OS fleets
One API boots Linux, Windows, macOS, and Android machines through local runtimes or Cua Cloud.
03
Batch throughput
Claim pre-booted machines in milliseconds from formally verified warm pools that scale to zero when idle.
FLEET COVERAGE
Run one rollout layer across four OS families.
LINUXBrowser and code work.
Run Ubuntu containers or full VMs with browser, terminal, Python, and package installs.
WINDOWSNative desktop work.
Run Windows 11 and Server 2025 for native apps, legacy software, and file workflows.
MACOSFleets on Apple Silicon.
Explore Cloud macOSRun Sequoia and Tahoe on Cua's patented virtualization stack, built to scale to thousands of machines.
ANDROIDTouch-first workflows.
Run Android VMs, install APKs, and automate taps, swipes, and multi-touch.
Products
From one sandbox to coordinated fleets.
Cua Sandbox
The computer-use runtime: boot disposable GUI environments through Python, locally or in Cua Cloud. Local backends include Docker, QEMU, and Apple VZ.
Cua Fleets
Elastic infrastructure that scales sandboxes into warm pools of machines you claim on demand for evals, RL loops, data generation, and batch rollouts.
SOC 2 Type IBYOC availableMIT licensedOn-prem available
Security and compliance detailsOpen-source control and eval layers: Cua Driver · Cua Bench · Lume
Open Core
It starts with Cua Driver, powering computer-use in Hermes, Clicky, H Company, and Factory Droid.
Cua Driver
The open-source background computer-use driver for native desktop apps. It lets agents click, type, scroll, inspect accessibility trees, and capture window state through the same MCP/CLI surface without stealing your cursor or focus.
Open-source and MIT licensed. One binary can run as an MCP stdio server, long-running daemon, or one-shot shell command on macOS, Windows, and Linux.
macOS + Windows + Linux
Native desktop backends preserve the user session across the major desktop OS families.
Drops into your stack
Run the same binary as an MCP stdio server, long-running daemon, or one-shot shell command.
MCP server + CLI
Exposes an MCP server and a CLI, so agents and humans drive the same harness.
Cua Sandbox
Local and cloud sandbox provisioning for agent training and evaluation.
Cua Bench
Eval and gym authoring for cross-surface agent benchmarks.
Lume
macOS VM management on Apple Silicon, built on Virtualization.framework.
SOC 2 Type IBYOC availableMIT licensedOn-prem available
Verified Data
Train against the environments, or take the verified data they produce.
Two ways to consume the same fleet, and either way the hard part is verifying the data.
Train against live environments
Point your training or eval loop at warm pools of real machines. Claim an environment on demand, step through the task, collect reward, and release it back. The pools are sized for large parallel batches.
Take the verified data they produce
Skip the harness entirely. We run the rollouts on the same environments and deliver verified trajectory datasets, packaged for your data-ingestion pipeline and scoped by task and surface.
Evaluators in the loop
Tasks can include evaluators that check whether a rollout completed the objective.
Human-reviewed golden trajectories
Human-reviewed golden trajectories and step-level annotations are available for selected scopes.
Acceptance you can set
Define the bar (target model, difficulty tier, surface mix) and we hold delivery to it before the data reaches your pipeline.
4 OS families
Linux, Windows, macOS, Android
1 driver surface
MCP + CLI across machines
19.6K
GitHub humans
Pricing
Scale computer fleets on your own infrastructure.
Run GUI Docker, QEMU, and Apple VZ sandboxes locally with the open-source Cua Sandbox framework. Move to hosted, BYOC, or on-prem infrastructure when your workloads need more concurrency.
Local sandbox framework on GitHub. Dedicated fleets by request.
