{"slug": "one-exe-no-python-no-docker-120-windows-automation-tools-written-in-go", "title": "One EXE. No Python. No Docker. 120 Windows automation tools written in Go.", "summary": "A developer built a Windows computer-use MCP server in pure Go, delivering a single 27 MB executable with 120 automation tools for local LLMs. The project, spanning over 14,000 lines of Go, implements vision, memory, and a training pipeline without dependencies on OpenCV or COM libraries. Created through pair-programming with multiple AI models, the tool enables LLMs to control a Windows desktop via mouse, keyboard, and screen interaction.", "body_md": "I built a Windows computer-use MCP server in pure Go. One EXE. No Python. No Docker.\n\nIt's a single **27 MB executable** that gives local LLMs (Claude, Gemini, Cursor, Kiro, OpenCode, Ollama, you name it) the ability to actually *use* a Windows desktop. Think of it as giving an LLM a mouse, keyboard, eyes, and long-term memory.\n\n*(Screenshots and demo clips coming soon — wanted to get the post up first.)*\n\nOver 14,000 lines of Go, zero dependencies on OpenCV, go-ole, or any COM binding library. Almost every subsystem was implemented from scratch in pure Go instead of wrapping existing libraries.\n\nI'm not a professional software engineer. I built this by pair-programming with multiple AI models across hundreds of iterations.\n\n**And I didn't spend a cent on API tokens.** Gemini CLI (free tier), Claude Code (trial credits), Ollama (local, free), GitHub Copilot, OpenCode's Big Pickle (200K ctx, free). The `ollama launch claude`\n\ntrick was a workhorse — point Claude Code at a Nemotron or MiniMax3 locally and get agentic scaffolding on budget hardware.\n\nThis started as \"I want my AI to click a button.\" It somehow turned into a Windows automation framework with vision, memory, and a training pipeline.\n\nBut the real reason? A friend who's disabled and uses Narrator as their primary computer interface. They asked for a month to test once I was ready to go public. After countless trials and Python's \"works on my machine\" nonsense, I wanted something that actually ships.\n\n**120 MCP tools** covering the full desktop stack:\n\n`find_image`\n\n/`find_all_images`\n\nwith triple cascade: template matching → ONNX YOLO → OCR`ocr_languages`\n\n, middle mouse, horizontal scroll, fullscreen detection**Battle-tested with:** Claude Desktop, Claude Code, Kiro, Cursor, Windsurf, Gemini CLI, OpenCode, Ollama, Antigravity IDE, Cline, Android Studio, Zed, Obsidian, and more.\n\n`syscall.SyscallN(vtblMethod(obj, N), ...)`\n\nwith indices hand-verified against Windows SDK headers.If you're building AI agents, this gives them hands.\n\nIf you're building desktop automation, this gives you 120 reusable tools.\n\nIf you're learning Windows internals, it shows how raw WinRT COM, OCR, ONNX, and UI automation fit together in a real project.\n\nIf you're just curious how far one person can get with modern AI tools, this is my answer.\n\nYes, it can control your computer. So can AutoHotkey, PowerShell, Selenium, and every RPA tool. This is **local-first**, every action can be logged, privacy controls toggle at runtime. Not spyware. Not a remote admin tool. Just an automation engine for your own machine.\n\nEspecially from people into Go, MCP, local AI, computer vision, automation, or Windows internals. Open issues, suggest features, steal patterns — the repo has templates and a security policy now. Tell me what I broke, what to build next, or that I'm insane for hand-writing COM vtables in Go.\n\nAI didn't build this project. AI became my pair programmer.\n\nThe architecture, direction, debugging, testing, and endless \"why doesn't Windows do what the docs say?\" moments were still mine.\n\n**It convinced me that one curious computer technician, persistence, and today's AI tools can build things I wouldn't have been able to create on my own just a few years ago.**\n\n**Links**\n\nGitHub: [https://github.com/coff33ninja/go-mcp-computer-use](https://github.com/coff33ninja/go-mcp-computer-use)\n\nDocs: `docs/reference/tools.md`\n\n, `docs/security.md`\n\n, `docs/mcp-client-configs.md`", "url": "https://wpnews.pro/news/one-exe-no-python-no-docker-120-windows-automation-tools-written-in-go", "canonical_source": "https://dev.to/coff33ninja/one-exe-no-python-no-docker-120-windows-automation-tools-written-in-go-i4m", "published_at": "2026-06-30 22:30:40+00:00", "updated_at": "2026-06-30 22:48:54.165489+00:00", "lang": "en", "topics": ["artificial-intelligence", "developer-tools", "computer-vision", "ai-agents", "machine-learning"], "entities": ["Claude", "Gemini", "Cursor", "Kiro", "OpenCode", "Ollama", "GitHub", "Windows"], "alternates": {"html": "https://wpnews.pro/news/one-exe-no-python-no-docker-120-windows-automation-tools-written-in-go", "markdown": "https://wpnews.pro/news/one-exe-no-python-no-docker-120-windows-automation-tools-written-in-go.md", "text": "https://wpnews.pro/news/one-exe-no-python-no-docker-120-windows-automation-tools-written-in-go.txt", "jsonld": "https://wpnews.pro/news/one-exe-no-python-no-docker-120-windows-automation-tools-written-in-go.jsonld"}}