Voice-driven AI professional agent. Real-time conversations powered by Gemini Live API, native audio streaming, and multimodal intelligence. BIM/Revit, financial analysis, and web search tools.
# CADRE·AI **Voice-controlled AI agent for architects, engineers, and business professionals.** [](https://ai.google.dev/) [](https://google.github.io/adk-docs/) [](https://cloud.google.com/run) [](LICENSE) > Built for the [Gemini Live Agent Challenge](https://googleai.devpost.com/) — March 2026 <p align="center"> <img src="assets/scene_03_tool_execution.png" alt="Cadre-AI Tool Execution" width="720"> </p> --- ## What It Does Cadre-AI lets you **talk** to your building model, financial data, and the web — all through natural voice conversation. Ask "How many rooms on Level 1?" and hear the answer instantly while watching MCP tools execute in real-time. Say "Create a wall on Level 2" and see it appear in Revit. This is **the first voice-controlled BIM automation agent** — nobody else has real-time Revit integration through voice. --- ## Architecture <p align="center"> <img src="architecture.svg" alt="Cadre-AI Architecture" width="800"> </p> **Local mode:** All 3 MCP toolsets active, including Revit via named pipe. **Cloud mode:** Financial + Web Search active. Revit disabled (`REVIT_ENABLED=false`). --- ## Features ### Architecture & BIM (25+ tools) - Query levels, rooms, walls, doors, windows, views, sheets - Create walls, doors, windows, rooms - Place views on sheets, add dimensions - Run QA/QC validation and compliance checks - Generate schedules and reports ### Financial Intelligence (13 tools) - Real-time stock quotes and market overview - Technical analysis (RSI, MACD, moving averages) - Fundamental analysis (P/E, revenue, earnings) - Portfolio tracking and risk analysis - News sentiment an
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.