NextDesk

NextDesk

AI that clicks, types, and thinks — right on your desktop.

6 followers

An intelligent desktop automation application powered by Google's Gemini AI that uses the ReAct (Reasoning + Acting) framework to understand and execute complex computer tasks through natural language commands.
NextDesk gallery image
NextDesk gallery image
NextDesk gallery image
NextDesk gallery image
NextDesk gallery image
Free
Launch tags:Developer ToolsGitHub
Launch Team / Built With
Wispr Flow: Dictation That Works Everywhere
Wispr Flow: Dictation That Works Everywhere
Stop typing. Start speaking. 4x faster.
Promoted

What do you think? …

Mohammed CHAHBOUN
Hey Product Hunt! 👋 I'm excited to introduce NextDesk — an intelligent desktop automation app powered by Google's Gemini AI. Unlike traditional macro tools, NextDesk uses the ReAct (Reasoning + Acting) framework to understand your natural language commands (like “open Chrome and search for Flutter docs”) and autonomously breaks them down into precise, executable steps — using keyboard shortcuts, mouse control, and real-time reasoning. 🔧 Key features: Full ReAct AI agent loop (Thought → Action → Observation) Reliable keyboard automation (pressKeys, getShortcuts) Local task history with Isar database Cross-platform (macOS, Windows, Linux) Privacy-first: all automation runs locally; only AI calls go to Gemini ⚠️ It’s still in active development (especially the vision-based detection), but the core workflow is already surprisingly powerful for power users, developers, and anyone tired of repetitive desktop tasks. I built this to make AI do the work, not just talk about it. Would love your feedback, bug reports, or ideas for use cases! Thanks for checking it out! 🙌