[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-862":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":13,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":22,"topics":24,"createdAt":10,"pushedAt":10,"updatedAt":29,"readmeContent":30,"aiSummary":31,"trendingCount":16,"starSnapshotCount":16,"syncStatus":32,"lastSyncTime":33,"discoverSource":34},862,"open-codex-computer-use","iFurySt\u002Fopen-codex-computer-use","iFurySt","👾 Open Computer Use – Open-Source Alternative to Codex Computer Use","",null,"Swift",1035,113,4,13,0,56,313,168,19.17,"MIT License",false,"main",[25,26,27,28],"codex-computer-use","computer-use","open-computer-use","open-computer-use-mcp","2026-06-12 02:00:19","# open-computer-use\n\n[![English](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FEnglish-Click-yellow)](.\u002FREADME.md)\n[![简体中文](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F简体中文-点击查看-orange)](.\u002FREADME.zh-CN.md)\n[![Release](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002FiFurySt\u002Fopen-codex-computer-use)](https:\u002F\u002Fgithub.com\u002FiFurySt\u002Fopen-codex-computer-use\u002Freleases)\n[![Ask DeepWiki](https:\u002F\u002Fdeepwiki.com\u002Fbadge.svg)](https:\u002F\u002Fdeepwiki.com\u002FiFurySt\u002Fopen-codex-computer-use)\n\u003Ca href=\"https:\u002F\u002Fllmapis.com?source=https%3A%2F%2Fgithub.com%2FiFurySt%2Fopen-codex-computer-use\" target=\"_blank\">\u003Cimg src=\"https:\u002F\u002Fllmapis.com\u002Fapi\u002Fbadge\u002FiFurySt\u002Fopen-codex-computer-use\" alt=\"LLMAPIS\" width=\"20\" \u002F>\u003C\u002Fa>\n\n---\n\n`open-computer-use` is an open-source `Computer Use` service wrapped as `MCP`. Any AI agent or MCP client can use it to run Computer Use on macOS, Linux, and Windows.\n\nThis project was inspired by OpenAI's [Codex Computer Use](https:\u002F\u002Fopenai.com\u002Findex\u002Fcodex-for-almost-everything\u002F). It showed that non-intrusive CUA can be built on top of Accessibility, so I decided to build an open-source version.\n\nI started this repo with my [harness template](https:\u002F\u002Fgithub.com\u002FiFurySt\u002Fharness-template), a template for quickly spinning up AI-first projects. It has been one of our most useful workflows lately, especially for nearly 100% AI-generated projects. I also wrote [a post](https:\u002F\u002Fwww.ifuryst.com\u002Fblog\u002F2026\u002Fspeedrunning-the-ai-era\u002F) about the methodology behind it.\n\n## Demos\n\n### Codex App and Codex CLI\n\n[![Open Computer Use custom demo cover](.\u002Fdocs\u002Fgenerated\u002Freadme-assets\u002Fopen-computer-use-demo-cover.png)](https:\u002F\u002Fyoutu.be\u002F2s6aVpGiwaQ)\n\n\u003Csub>\u003Cem>`open-computer-use` used as Computer Use in Codex App and Codex CLI, matching the official experience.\u003C\u002Fem>\u003C\u002Fsub>\n\n### Gemini CLI\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Feacb3b15-f939-46c7-b3b3-6f876977a58d\n\n\u003Csub>\u003Cem>Gemini CLI connects to `open-computer-use` through MCP and runs full Computer Use actions.\u003C\u002Fem>\u003C\u002Fsub>\n\n### Linux\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fe036b1c8-2200-4896-abd4-19225915cf66\n\n\u003Csub>\u003Cem>`open-computer-use` running on Linux.\u003C\u002Fem>\u003C\u002Fsub>\n\n## Quick Start\n\n```bash\nnpm i -g open-computer-use\n```\n\n**On macOS, run it once and grant `Accessibility` and `Screen Recording`. Windows and Linux do not need this step.**\n\n```bash\nopen-computer-use\n```\n\nBefore using it, install it into your agent:\n\n```bash\n# Install into Codex by writing to ~\u002F.codex\u002Fconfig.toml\nopen-computer-use install-codex-mcp\n```\n\nOr add it to your own client manually:\n\n```json\n{\n  \"mcpServers\": {\n    \"open-computer-use\": {\n      \"command\": \"open-computer-use\",\n      \"args\": [\"mcp\"]\n    }\n  }\n}\n```\n\n## More\n\nBesides the MCP JSON config above, you can also use the built-in commands:\n\n```bash\n# Install into Codex by writing to ~\u002F.codex\u002Fconfig.toml\nopen-computer-use install-codex-mcp\n\n# Install as a Codex plugin, mainly for Codex App\nopen-computer-use install-codex-plugin\n\n# Install into Claude Code by writing to ~\u002F.claude.json\nopen-computer-use install-claude-mcp\n\n# Install into Gemini CLI for the current project by writing to .\u002F.gemini\u002Fsettings.json\nopen-computer-use install-gemini-mcp\n\n# Install into Gemini CLI user config instead\nopen-computer-use install-gemini-mcp --scope user\n\n# Install into opencode by writing to ~\u002F.config\u002Fopencode\u002Fopencode.json (or the active config file)\nopen-computer-use install-opencode-mcp\n\n# Call a single Computer Use tool and print the MCP-style JSON result\nopen-computer-use call list_apps\nopen-computer-use call get_app_state --args '{\"app\":\"TextEdit\"}'\n\n# Run a sequence in one process so element_index state can be reused\n# Sequence runs sleep 1s between successful operations by default\nopen-computer-use call --calls '[{\"tool\":\"get_app_state\",\"args\":{\"app\":\"TextEdit\"}},{\"tool\":\"press_key\",\"args\":{\"app\":\"TextEdit\",\"key\":\"Return\"}}]'\nopen-computer-use call --calls-file examples\u002Ftextedit-overlay-seq.json --sleep 0.5\n\n# Check permissions; onboarding only opens when something is missing\nopen-computer-use doctor\n\n# Show help\nopen-computer-use -h\n```\n\n## Cursor Motion\n\nCursor Motion is an open-source cursor motion system for macOS, based on public information shared by members of the Software.Inc team. You can download the app from the [Releases page](https:\u002F\u002Fgithub.com\u002FiFurySt\u002Fopen-codex-computer-use\u002Freleases).\n\n[![Cursor Motion custom demo cover](.\u002Fdocs\u002Fgenerated\u002Freadme-assets\u002Fcursor-motion-demo-cover.png)](https:\u002F\u002Fyoutu.be\u002FKRUq5GUHv1Q)\n\n## Star History\n\n\u003Ca href=\"https:\u002F\u002Fwww.star-history.com\u002F?repos=iFurySt%2Fopen-codex-computer-use&type=date&legend=top-left\">\n  \u003Cpicture>\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=ifuryst\u002Fopen-codex-computer-use&type=date&theme=dark&legend=top-left\" \u002F>\n    \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=ifuryst\u002Fopen-codex-computer-use&type=date&legend=top-left\" \u002F>\n    \u003Cimg alt=\"Star History Chart for open-computer-use\" src=\"https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=ifuryst\u002Fopen-codex-computer-use&type=date&legend=top-left\" \u002F>\n  \u003C\u002Fpicture>\n\u003C\u002Fa>\n\n## License\n\n[MIT](.\u002FLICENSE)\n","`open-computer-use` 是一个开源的计算机使用服务，封装为 MCP 格式，允许任何 AI 代理或 MCP 客户端在 macOS、Linux 和 Windows 上执行计算机操作。该项目的核心功能是通过 Accessibility 接口实现非侵入式的计算机使用自动化，灵感来源于 OpenAI 的 Codex Computer Use 项目。它支持多种平台，并且可以通过简单的命令行安装和配置，适用于需要自动化计算机任务的场景，如软件测试、日常任务自动化等。其简洁的安装步骤和广泛的兼容性使得它成为开发者和自动化爱好者的一个强大工具。",2,"2026-06-11 02:39:50","CREATED_QUERY"]