{"id":26509442,"url":"https://github.com/trycua/cua","last_synced_at":"2026-04-15T23:04:32.931Z","repository":{"id":275168507,"uuid":"925270205","full_name":"trycua/cua","owner":"trycua","description":"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).","archived":false,"fork":false,"pushed_at":"2026-03-24T15:16:27.000Z","size":171710,"stargazers_count":13243,"open_issues_count":149,"forks_count":819,"subscribers_count":52,"default_branch":"main","last_synced_at":"2026-03-24T16:19:59.546Z","etag":null,"topics":["agent","ai-agent","apple","computer-use","computer-use-agent","containerization","cua","desktop-automation","hacktoberfest","lume","macos","manus","operator","swift","virtualization","virtualization-framework","windows","windows-sandbox"],"latest_commit_sha":null,"homepage":"https://cua.ai","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/trycua.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":".github/FUNDING.yml","license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":{"github":"trycua","patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"lfx_crowdfunding":null,"polar":null,"buy_me_a_coffee":null,"thanks_dev":null,"custom":null}},"created_at":"2025-01-31T15:02:49.000Z","updated_at":"2026-03-24T11:13:13.000Z","dependencies_parsed_at":"2025-12-29T06:08:40.843Z","dependency_job_id":"c656ccd4-feb7-4ec4-9540-76dc1a4a71a9","html_url":"https://github.com/trycua/cua","commit_stats":null,"previous_names":["trycua/lume","trycua/cua","trycua/computer"],"tags_count":546,"template":false,"template_full_name":null,"purl":"pkg:github/trycua/cua","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trycua%2Fcua","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trycua%2Fcua/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trycua%2Fcua/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trycua%2Fcua/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/trycua","download_url":"https://codeload.github.com/trycua/cua/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trycua%2Fcua/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31291151,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-01T13:12:26.723Z","status":"ssl_error","status_checked_at":"2026-04-01T13:12:25.102Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent","ai-agent","apple","computer-use","computer-use-agent","containerization","cua","desktop-automation","hacktoberfest","lume","macos","manus","operator","swift","virtualization","virtualization-framework","windows","windows-sandbox"],"created_at":"2025-03-21T01:01:29.686Z","updated_at":"2026-04-01T19:35:50.627Z","avatar_url":"https://github.com/trycua.png","language":"Python","readme":"\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://cua.ai\" target=\"_blank\" rel=\"noopener noreferrer\"\u003e\n    \u003cpicture\u003e\n      \u003csource media=\"(prefers-color-scheme: dark)\" alt=\"Cua logo\" width=\"150\" srcset=\"img/logo_white.png\"\u003e\n      \u003csource media=\"(prefers-color-scheme: light)\" alt=\"Cua logo\" width=\"150\" srcset=\"img/logo_black.png\"\u003e\n      \u003cimg alt=\"Cua logo\" width=\"500\" src=\"img/logo_black.png\"\u003e\n    \u003c/picture\u003e\n  \u003c/a\u003e\n\n  \u003cp align=\"center\"\u003eBuild, benchmark, and deploy agents that use computers\u003c/p\u003e\n\n  \u003cp align=\"center\"\u003e\n    \u003ca href=\"https://cua.ai\" target=\"_blank\" rel=\"noopener noreferrer\"\u003e\u003cimg src=\"https://img.shields.io/badge/cua.ai-0ea5e9\" alt=\"cua.ai\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://discord.com/invite/cua-ai\" target=\"_blank\" rel=\"noopener noreferrer\"\u003e\u003cimg src=\"https://img.shields.io/badge/Discord-Join%20Server-10b981?logo=discord\u0026logoColor=white\" alt=\"Discord\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://x.com/trycua\" target=\"_blank\" rel=\"noopener noreferrer\"\u003e\u003cimg src=\"https://img.shields.io/twitter/follow/trycua?style=social\" alt=\"Twitter\"\u003e\u003c/a\u003e\n    \u003ca href=\"https://cua.ai/docs\" target=\"_blank\" rel=\"noopener noreferrer\"\u003e\u003cimg src=\"https://img.shields.io/badge/Docs-0ea5e9.svg\" alt=\"Documentation\"\u003e\u003c/a\u003e\n    \u003cbr\u003e\n\u003ca href=\"https://trendshift.io/repositories/13685\" target=\"_blank\"\u003e\u003cimg src=\"https://trendshift.io/api/badge/repositories/13685\" alt=\"trycua%2Fcua | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"/\u003e\u003c/a\u003e\n  \u003c/p\u003e\n\n\u003c/div\u003e\n\n**Cua** is an open-source platform for building, benchmarking, and deploying agents that can use any computer, with isolated, self-hostable sandboxes (Docker, QEMU, Apple Vz).\n\n\u003cdiv align=\"center\"\u003e\n  \u003cvideo src=\"https://github.com/user-attachments/assets/c619b4ea-bb8e-4382-860e-f3757e36af20\" width=\"600\" controls\u003e\u003c/video\u003e\n\u003c/div\u003e\n\n## Choose Your Path\n\n\u003ctable width=\"100%\"\u003e\n  \u003ctr\u003e\n    \u003cth width=\"180\"\u003e\u003c/th\u003e\n    \u003cth align=\"left\"\u003eIf you want to...\u003c/th\u003e\n    \u003cth width=\"120\"\u003eCheck out\u003c/th\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003ca href=\"#cua---agentic-ui-automation--code-execution\"\u003e\u003cimg src=\"img/cua-architecture.png\" width=\"180\"\u003e\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003eBuild AI agents that interact with any desktop, or run isolated code execution environments for AI coding assistants\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"#cua---agentic-ui-automation--code-execution\"\u003e\u003cstrong\u003eCua\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003ca href=\"#cua-bench---benchmarks--rl-environments\"\u003e\u003cimg src=\"img/cua-bench-architecture.png\" width=\"180\"\u003e\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003eBenchmark computer-use models on standardized tasks, or train agents with reinforcement learning\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"#cua-bench---benchmarks--rl-environments\"\u003e\u003cstrong\u003eCua-Bench\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003ca href=\"#lume---macos-virtualization\"\u003e\u003cimg src=\"img/lume-architecture.png\" width=\"180\"\u003e\u003c/a\u003e\u003c/td\u003e\n    \u003ctd\u003eRun macOS and Linux VMs at near-native speed on Apple Silicon for CI/CD, testing, or agent workloads\u003c/td\u003e\n    \u003ctd\u003e\u003ca href=\"#lume---macos-virtualization\"\u003e\u003cstrong\u003eLume\u003c/strong\u003e\u003c/a\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n---\n\n## Cua - Agentic UI Automation \u0026 Code Execution\n\nBuild agents that see screens, click buttons, and complete tasks autonomously. Run isolated code execution environments for AI coding assistants like Claude Code, Codex CLI, or OpenCode.\n\n\u003cimg src=\"img/cua-architecture.png\" alt=\"Cua Architecture\" width=\"100%\"\u003e\n\n```python\n# Requires Python 3.12 or 3.13\nfrom computer import Computer\nfrom agent import ComputerAgent\n\ncomputer = Computer(os_type=\"linux\", provider_type=\"cloud\")\nagent = ComputerAgent(model=\"anthropic/claude-sonnet-4-5-20250929\", computer=computer)\n\nasync for result in agent.run([{\"role\": \"user\", \"content\": \"Open Firefox and search for Cua\"}]):\n    print(result)\n```\n\n**[Get Started](https://cua.ai/docs/cua/guide/get-started/set-up-sandbox)** | **[Examples](https://cua.ai/docs/cua/examples)** | **[API Reference](https://cua.ai/docs/cua/reference/agent-sdk)**\n\n---\n\n## Cua-Bench - Benchmarks \u0026 RL Environments\n\nEvaluate computer-use agents on OSWorld, ScreenSpot, Windows Arena, and custom tasks. Export trajectories for training.\n\n\u003cimg src=\"img/cua-bench-architecture.png\" alt=\"Cua-Bench Architecture\" width=\"100%\"\u003e\n\n```bash\n# Install and create base image\ncd cua-bench\nuv tool install -e . \u0026\u0026 cb image create linux-docker\n\n# Run benchmark with agent\ncb run dataset datasets/cua-bench-basic --agent cua-agent --max-parallel 4\n```\n\n**[Get Started](https://cua.ai/docs/cuabench/guide/getting-started/first-steps)** | **[Registry](https://cuabench.ai/registry)** | **[CLI Reference](https://cua.ai/docs/cuabench/reference/cli-reference)**\n\n---\n\n## Lume - macOS Virtualization\n\nCreate and manage macOS/Linux VMs with near-native performance on Apple Silicon using Apple's Virtualization.Framework.\n\n\u003cimg src=\"img/lume-architecture.png\" alt=\"Lume Architecture\" width=\"100%\"\u003e\n\n```bash\n# Install Lume\n/bin/bash -c \"$(curl -fsSL https://raw.githubusercontent.com/trycua/cua/main/libs/lume/scripts/install.sh)\"\n\n# Pull \u0026 start a macOS VM\nlume run macos-sequoia-vanilla:latest\n```\n\n**[Get Started](https://cua.ai/docs/lume)** | **[FAQ](https://cua.ai/docs/lume/guide/getting-started/faq)** | **[CLI Reference](https://cua.ai/docs/lume/reference/cli-reference)**\n\n---\n\n## Packages\n\n| Package                                                               | Description                                                |\n| --------------------------------------------------------------------- | ---------------------------------------------------------- |\n| [cua-agent](https://cua.ai/docs/cua/reference/agent-sdk)              | AI agent framework for computer-use tasks                  |\n| [cua-computer](https://cua.ai/docs/cua/reference/computer-sdk)        | SDK for controlling desktop environments                   |\n| [cua-computer-server](https://cua.ai/docs/cua/reference/computer-sdk) | Driver for UI interactions and code execution in sandboxes |\n| [cua-bench](https://cua.ai/docs/cuabench)                             | Benchmarks and RL environments for computer-use            |\n| [lume](https://cua.ai/docs/lume)                                      | macOS/Linux VM management on Apple Silicon                 |\n| [lumier](https://cua.ai/docs/lume/guide/advanced/lumier)              | Docker-compatible interface for Lume VMs                   |\n\n## Resources\n\n- [Documentation](https://cua.ai/docs) — Guides, examples, and API reference\n- [Blog](https://www.cua.ai/blog) — Tutorials, updates, and research\n- [Discord](https://discord.com/invite/mVnXXpdE85) — Community support and discussions\n- [GitHub Issues](https://github.com/trycua/cua/issues) — Bug reports and feature requests\n\n## Contributing\n\nWe welcome contributions! See our [Contributing Guidelines](CONTRIBUTING.md) for details.\n\n## License\n\nMIT License — see [LICENSE](LICENSE.md) for details.\n\nThird-party components have their own licenses:\n\n- [Kasm](libs/kasm/LICENSE) (MIT)\n- [OmniParser](https://github.com/microsoft/OmniParser/blob/master/LICENSE) (CC-BY-4.0)\n- Optional `cua-agent[omni]` includes ultralytics (AGPL-3.0)\n\n## Trademarks\n\nApple, macOS, Ubuntu, Canonical, and Microsoft are trademarks of their respective owners. This project is not affiliated with or endorsed by these companies.\n\n---\n\n\u003cdiv align=\"center\"\u003e\n\n[![Stargazers over time](https://starchart.cc/trycua/cua.svg?variant=adaptive)](https://starchart.cc/trycua/cua)\n\nThank you to all our [GitHub Sponsors](https://github.com/sponsors/trycua)!\n\n\u003cimg width=\"300\" alt=\"coderabbit-cli\" src=\"https://github.com/user-attachments/assets/23a98e38-7897-4043-8ef7-eb990520dccc\" /\u003e\n\n\u003c/div\u003e\n","funding_links":["https://github.com/sponsors/trycua","https://github.com/sponsors/trycua)!"],"categories":["Developer Tools","HTML","Python","agent","windows","A01_文本生成_文本对话","Repos","Agent Integration \u0026 Deployment Tools","Tools","Table of Contents","Open Source Agents","Agent Runtime Infrastructure","Agents \u0026 Orchestration"],"sub_categories":["Robotics \u0026 Automation","大语言对话模型及数据","MCP Server Framework","Computer Use","Agent","Codex Resources"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrycua%2Fcua","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftrycua%2Fcua","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrycua%2Fcua/lists"}