# trycua/cua

Scale computer-use 2.0 with open-source drivers, cross-OS fleets, and benchmarks for training, evaluation, and data generation.

Repository: https://github.com/trycua/cua
Canonical: https://ross.abutalabs.com/products/cua
Homepage: https://cua.ai
Language: HTML
License: MIT
License Family: permissive
Topics: apple, cua, lume, macos, virtualization, virtualization-framework, swift, ai-agent, computer-use, manus, operator, agent, containerization, windows, windows-sandbox, hacktoberfest, computer-use-agent, desktop-automation
Last push: 2026-08-26T23:56:22+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 41
- inputs: {"age_days": 579, "days_push": 7, "days_rel": 11, "gap_med": 0, "n_releases_24m": 550}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 21922, forks 1508 (observed 2026-08-28T04:11:32.201918+00:00)

## What it is
Cua is an open-source framework for computer-use agents, providing background desktop drivers, disposable GUI sandboxes, cross-OS fleets (Linux, Windows, macOS, Android), and Cua-Bench for verifiable task benchmarks and RL environments. It includes Lume for Apple Silicon macOS virtualization and a Python SDK for running, evaluating, and generating training data from agent workloads.

## Use cases
- run computer-use agents on real desktops in the background
- spin up disposable GUI sandboxes for AI agents
- benchmark and evaluate computer-use models on verifiable tasks
- generate training data from agent desktop activity
- run macOS VMs on Apple Silicon locally
- scale agent evals across parallel cloud fleets
- let a coding agent drive native desktop apps without taking over the cursor
- run reinforcement learning environments for desktop agents

## When to choose
- you are building or evaluating computer-use agents and need real or isolated desktop environments
- you need cross-OS (Linux, Windows, macOS, Android) agent infrastructure with one API
- you want open-source, self-hostable VM and sandbox runtimes including macOS on Apple Silicon
- you need repeatable, verifiable benchmarks or RL environments for desktop tasks

## When to avoid
- you only need simple browser automation or web scraping without a full desktop
- you need a managed no-code RPA product rather than a developer framework
- your agents only interact with APIs and never need GUI or desktop control

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, machine-learning, benchmarking, simulation, workflow-automation, sdk, cli, mcp
- domain: artificial-intelligence, reinforcement-learning, developer-tools, cross-platform
- platform: windows, python, cloud, self-hosted, cross-platform
- tags: computer-use, computer-use-agents, desktop-automation, virtualization, macos-vms, apple-silicon, sandboxing, rl-environments, agent-evaluation, data-generation, gui-automation, fleets, ai-agents, automation, macos, linux, android, docker

## Member repositories
- trycua/cua (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:32.201918+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:57:45.307348+00:00, confidence not recorded.
  - readme: https://github.com/trycua/cua (fetched 2026-08-28T04:11:32.201918+00:00, sha b405f8a585e6)
  - homepage: https://cua.ai (fetched 2026-08-29T07:56:09.593323+00:00, sha 51dd5251cc1a)
  - site_page: https://cua.ai/docs (fetched 2026-08-29T07:56:09.597996+00:00, sha b37a59dff341)
  - site_page: https://cua.ai/docs/how-to-guides (fetched 2026-08-29T07:56:09.599872+00:00, sha 542f1531a40e)
  - site_page: https://cua.ai/about (fetched 2026-08-29T07:56:09.603252+00:00, sha f8ef31f19346)
  - site_page: https://cua.ai/docs/how-to-guides/sandbox/scale-out (fetched 2026-08-29T07:56:09.605108+00:00, sha 9c1b4c11d49f)
  - site_page: https://cua.ai/docs/tutorials/your-first-cloud-fleet (fetched 2026-08-29T07:56:09.606817+00:00, sha e6ba9d251664)
  - site_page: https://cua.ai/docs/tutorials/drive-your-first-app (fetched 2026-08-29T07:56:09.608411+00:00, sha 08d1f713e66e)
  - site_page: https://cua.ai/docs/concepts/what-is-cua-bench (fetched 2026-08-29T07:56:09.610149+00:00, sha ea6564c2e077)
  - site_page: https://cua.ai/changelog (fetched 2026-08-29T07:56:09.601510+00:00, sha 7db073151523)
- Data as of 2026-08-30T08:39:29.467469+00:00.