AleksNeStu/ai-real-estate-assistant

Open-source AI real estate search with RAG, vector search, multi-provider LLMs, FastAPI, Next.js, ChromaDB, and a live demo.

What it solves

This project provides a conversational AI platform designed to simplify property searching and real estate market analysis. It allows users to find listings using natural language queries instead of rigid filters, while providing integrated financial tools for investment and mortgage calculations.

How it works

The system uses a hybrid architecture that combines a FastAPI backend with a Next.js frontend. It employs a Query Analyzer to route requests based on complexity: simple queries go to a RAG (Retrieval-Augmented Generation) engine using ChromaDB for semantic search, while complex queries are handled by a hybrid agent with access to specialized tools. The platform supports multiple LLM providers (including OpenAI, Anthropic, and local Ollama) with an automatic fallback chain to ensure reliability.

Who it’s for

Real estate seekers, investors, and agents who want a more intuitive, AI-driven way to search for properties and analyze market value and neighborhood characteristics.

Highlights

  • Multi-Provider AI Routing: Supports 13 LLM providers with the ability to switch models via headers without code changes.
  • Hybrid Search: Combines semantic and keyword search with MMR reranking for improved relevance.
  • Financial Analytics: Includes a mortgage calculator, ROI analysis, and AI-powered price forecasting with multi-year projections.
  • Multilingual Support: Available in 9 languages with EU AI Act compliance labels.
  • Enterprise-Ready Security: Features OWASP-hardened security, rate limiting, and dual-mode authentication.

Related

  • Project
    nlweb-ai/NLWeb

    A set of open protocols and tools to build conversational interfaces for websites, enabling both humans and AI agents to interact with web content using natural language.

  • Project
    agentpit-io/hunter-community

    Hunter Community Edition is an open‑source, Docker‑compose‑deployed financial AI agent platform. With a single LLM API key it provides real‑time market data (32+ sources), 23 pre‑built analysis SKILLs, a local “investment thesis” memory, and plug‑and‑play model compatibility (DeepSeek, Claude, Qwen, etc.). Everything runs on the user’s machine—data, chat history, and thesis stay on local disk—while remaining extensible via custom Markdown SKILLs or user‑provided MCP data services.

  • Project
    YUHAI0/fin-agent

    An AI-powered financial analysis assistant that uses LLMs and Tushare data to enable natural language stock screening, strategy backtesting, and portfolio monitoring.

  • Project
    dnhkng/GLaDOS

    A multi-modal, autonomous AI persona framework that creates a proactive voice assistant with vision, long-term memory, and a low-latency response pipeline.

  • Project
    Azure-Samples/rag-postgres-openai-python

    A web-based chat application that uses RAG to answer questions about PostgreSQL database rows using hybrid search and OpenAI function calling.