PropVector AI

The PropVector AI Agentic OS screen: a dark interface listing the six specialised agents - Property Search, Comparative Market Analysis, Market Analyst, Lead Scoring, Market Anomaly Detector and Legal Review - each with its version, a description, an example query and a link to its detail page. — PropVector AI’s Agentic OS, running from the product’s own build (English locale). Captured 2026-11-01.

How it works

Three steps from feed to follow-up.

01
Connect your feed
Live MLS listings flow into the vector index, so search is always on current stock.
- Documents and listings indexed into your own knowledge base
- Questions answered from it, with the citation attached
- The index runs on your machine, not on ours
02
Search by meaning
Agents and buyers describe the home; vector search finds it, in any of nine languages.
- The query is typed the way a buyer would say it
- Filters for price, area, rooms and type
- Results exported to CSV with the columns you choose
03
Value it and follow up
CMA and ROI on each listing, a multi-year forecast, and saved searches that feed the AI CRM.
- CMA in five steps: subject, comparables, adjustments, preview, export
- Mortgage, ROI and price analysis in the same workspace
- Saved searches that feed the AI CRM

In development. Pilot partnerships open for Q1 2027.

Ask about PropVector AI

The workspace

More than the three steps.

The agent directory and the assistant run beside the same index — the same screens a broker works in.

The PropVector AI Agentic OS screen: the directory of available agents, each with its own description, example query and capabilities.

The PropVector AI Assistant chat screen: the conversational surface over the same property index.

Who it is for

Built for three kinds of team.

01

Brokerages

Your agents search by feel, and your site still searches by price, beds and baths.

02

PropTech platforms

You need semantic search, valuation and saved searches without building the stack.

03

OpenStore users

You run the open-source version and now need live data, accounts and an uptime SLA.

Capabilities

What it does.

01

Semantic vector search

ChromaDB-powered natural-language listing search. Query like "2-bedroom apartment in Kraków under 500k" and get matched results.

02

MLS integrations

Live property feeds across multiple MLS databases. Real-time listing pricing, status, and availability.

03

9 languages, native

English, Polish, Russian, German, Spanish, Italian, Portuguese, Turkish, Ukrainian. Multilingual UI and multilingual LLM prompts.

04

Financial tooling

Mortgage calculator, rent-vs-buy comparison, ROI analysis, TCO calculator, CMA reports. Built for brokers and PropTech.

05

Multi-year price forecast

AI property valuation with 1y, 3y, 5y, 10y forward-looking price forecast. Trained on per-market historical data.

06

Interactive maps

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

Open-source twin

OpenStore

The OSS sibling of PropVector AI: open-source AI real-estate search with 320 GitHub stars and 120 forks, MIT licensed. Same architectural primitives, broader audience.

Read about OpenStore

Case study

How this product came about, and where it actually stands.

Problem. Real-estate search runs on filters and keywords. Brokers and PropTech platforms need semantic search that understands "quiet neighborhood with good schools" or "investment property with high ROI potential" — not just price + beds + baths.

Approach. Dual strategy. Public open-source (OpenStore) ships the core architecture: ChromaDB vector search, MMR reranking, 16 LLM providers, 9 languages, financial tooling, multi-year price forecast. Commercial tier (PropVector AI) layers live MLS feeds, accounts, favorites, saved searches, AI CRM, and an uptime SLA.

Status as of October 2026. OpenStore public OSS at 320 GitHub stars and 120 forks, MIT-licensed, continuously maintained since 2024. Commercial build running on our own EU infrastructure with the full production stack; it has no public URL yet, so the OSS repo is the part you can inspect today. Billing is wired for paid tiers. No commercial-result metrics publicly verifiable as of October 2026.

Trust signals

Proof close to the decision.

Three signals buyers can verify before they start a conversation.

01

EU data residency by default

Product runtimes on our own infrastructure across the EU (Germany, France) and North America (Canada). See our security posture.

02

Founder-led delivery

The person you contact stays close to the work, from written scope through operation. See how we work.

03

Open-source track record

OpenStore is MIT-licensed and public, with 320 GitHub stars and 120 forks. Inspect the foundation.

Questions

About PropVector AI.

How is PropVector AI different from OpenStore?

OpenStore is the open-source core. PropVector AI adds live MLS feeds, accounts, favourites, saved searches, an AI CRM and an uptime SLA.

Which languages does search support?

Nine languages, with prompts tuned for real-estate queries.

When can we use it?

PropVector AI is in development. Pilot partnerships are open for Q1 2027 through the contact form.

Can we export search results and valuation reports?

Yes. Search results export to CSV with the columns you choose, and CMA reports run in five steps: subject, comparables, adjustments, preview and export. AI property valuation adds 1y, 3y, 5y and 10y forward-looking price forecasts, trained on per-market historical data. The financial tooling covers a mortgage calculator, rent-vs-buy comparison, ROI analysis and TCO calculator.