An AI-powered computer-use agent built with Electron. Automate desktop tasks by letting AI see and interact with your OS.
<p align="center"> <img src="build/icon.png" width="128" height="128" alt="Atlas" /> </p> <h1 align="center">Atlas</h1> <p align="center"> <b>AI agent that lives on your desktop.</b><br/> It sees your screen, understands what you need, and gets things done — hands-free. </p> <p align="center"> <a href="https://github.com/dortanes/atlas/releases"><img src="https://img.shields.io/badge/download-v0.2.3-7c3aed?style=for-the-badge&logo=windows&logoColor=white" alt="Download" /></a> <a href="#-getting-started"><img src="https://img.shields.io/badge/get%20started-→-0ea5e9?style=for-the-badge" alt="Get Started" /></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-gray?style=for-the-badge" alt="License" /></a> </p> <p align="center"> <img src="https://img.shields.io/badge/Windows-supported-brightgreen?style=flat-square&logo=windows&logoColor=white" alt="Windows" /> <img src="https://img.shields.io/badge/macOS%20%26%20Linux-coming%20soon-yellow?style=flat-square" alt="macOS & Linux" /> <img src="https://img.shields.io/badge/privacy--first-local%20only-blue?style=flat-square" alt="Privacy" /> </p> <p align="center"><img src="docs/preview.png" width="300" alt="Atlas Demo" /></p> --- > **⚠️ Atlas is in active development (v0.2.3).** > > - 🤖 **LLM support:** Gemini (including native [Computer Use API](https://ai.google.dev/gemini-api/docs/computer-use)) and OpenAI. More providers on the way. > - 🖥 **Screen control:** Gemini 3.x models use native [Computer Use API](https://ai.google.dev/gemini-api/docs/computer-use) for precise actions. Older models use vision-based coordinate prediction. > - 💻 **Platform:** Windows only for now. macOS & Linux support is planned. > - 🐛 **Found a bug?** We'd love to hear about it — [open an issue](https://github.com/dortanes/atlas/issues). --- ## What is Atlas? Atlas is an **AI-powered desktop agent** that works alongside you as a transparent overlay. Press `Ctrl+Space`, t
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.