OpenStore
Open-source AI real-estate search. 285 GitHub stars, MIT licensed. RAG + ChromaDB + 13 LLM providers + 9 languages. The OSS sibling of PropVector AI.
AleksNeStu/ai-real-estate-assistant
Maintained by @AleksNeStu on GitHub.
The thesis.
Real-estate listings are public data. The search layer on top of them shouldn't be a walled garden. OpenStore is the public, working version of our real-estate stack — and the credibility proof for PropVector AI.
What it ships.
13 LLM providers
OpenAI, Anthropic, Google, Grok, DeepSeek, and local Ollama. Switch providers without code changes.
Hybrid RAG + ChromaDB
Vector search with MMR reranking. Retrieval-augmented generation pulls live data into the prompt.
9 languages
English, Polish, Russian, German, Spanish, Italian, Portuguese, Turkish, Ukrainian. Native UI + native LLM prompts.
Natural-language search
Ask like "2-bedroom apartment in Kraków under 500k". Automatic filter extraction from the query.
Financial tools
Mortgage calculator, rent-vs-buy, ROI, TCO, CMA reports. AI property valuation with 1y / 3y / 5y / 10y forecasts.
Interactive maps
Property clustering, area analytics, neighborhood one-liner summaries on property detail pages.
From OpenStore to PropVector AI.
OpenStore ships the core architecture. PropVector AI is the commercially hardened version: live MLS data feeds, accounts, favorites, saved searches, AI CRM, enterprise features. Same primitives, more constraints.
Want to contribute?
Issues, PRs, and feature requests welcome on GitHub.
Open issues →