We're excited to share the latest progress on Nexus, our open-source, MCP-powered AI personal workspace developed for the Amazon Developer Hackathon — Alexa+ Track.
Nexus has evolved from a simple AI assistant concept into a full-stack intelligent workspace that connects productivity tools, development services, and everyday utilities through natural-language interactions.
The platform currently features 30 MCP tools and 11 interactive dashboard views, built using React, Node.js, and Express. It integrates Google Calendar, Gmail, Google Tasks, GitHub, and weather services, allowing users to manage multiple workflows from one unified interface.
We've also implemented voice interactions using Whisper Large V3, supporting English and Hinglish commands. Groq Cloud and Qwen power conversational AI, intelligent request interpretation, and tool orchestration.
Security has been a major priority throughout development. Nexus includes encrypted credential storage, secure authentication, human-in-the-loop approval for sensitive actions, audit logging, and post-execution verification. Our documented automated test run achieved 51 passing tests.
Another important milestone is our self-hosted MCP server, which enables standardized communication between AI assistants and connected tools. We've also developed an Alexa+ Lab simulation environment to explore and test Alexa+-style interactions.
Nexus is now live and open source!
Live Demo: https://nexus-2-pus3.onrender.com/
GitHub Repository: https://github.com/Sachin1707-jpg/Nexus
Moving forward, we plan to explore deeper Alexa+ integration, additional MCP connectors, improved voice capabilities, and more advanced automation workflows.
Our vision is to build an AI workspace that goes beyond answering questions and helps users complete meaningful tasks securely, efficiently, and transparently.
We welcome feedback, suggestions, and contributions from the developer community.
Log in or sign up for Devpost to join the conversation.