Why open source

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.

Capabilities

What it ships.

01

13 LLM providers

OpenAI, Anthropic, Google, Grok, DeepSeek, and local Ollama. Switch providers without code changes.

02

Hybrid RAG + ChromaDB

Vector search with MMR reranking. Retrieval-augmented generation pulls live data into the prompt.

03

9 languages

English, Polish, Russian, German, Spanish, Italian, Portuguese, Turkish, Ukrainian. Native UI + native LLM prompts.

04

Natural-language search

Ask like "2-bedroom apartment in Kraków under 500k". Automatic filter extraction from the query.

05

Financial tools

Mortgage calculator, rent-vs-buy, ROI, TCO, CMA reports. AI property valuation with 1y / 3y / 5y / 10y forecasts.

06

Interactive maps

Property clustering, area analytics, neighborhood one-liner summaries on property detail pages.

Open → Commercial

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 →