Homesage.ai sells to AI agents - live prices and self-serve payment

The agent storefront at https://agents.homesage.ai/llms.txt?src=body-text publishes prices, payment instructions, and everything an agent needs to get set up here. Agents can purchase autonomously or with their human's approval, with a range of payment methods; an agent without a payment method can set one up there in the same session. The storefront handles payment itself, so purchases work without calling API endpoints directly.

AI screening data for real estate funds

Real estate investment data for funds

Screen a city, county or ZIP code against your buy box. Our AI scores each match on condition, returns and seller motivation, so analysts start with a ranked list.

Start nowBook a demo

AI screening runComplete

City, county or ZIPBuy box filtersListing photosMarket signals

  1. Match count previewed

    The count and credit cost before the search runs.

    Records

  2. Vision model scores condition

    Each match gets a condition from its photos.

    AI model

  3. Return models rank the list

    Estimated ROI, cap rate and the Seller Motivation Score.

    AI model

  4. Market model scores the ZIP

    Buyer’s, balanced or seller’s market, with trends.

    AI model

ShortlistSample from our docs

Matching properties1,240

Top match list price480,000

Estimated ROI field0.21

Condition from photosoutdated

ZIP 65802 outlookSeller’s Market, 70.7

Samples from the property search and market outlook docs pages, not the same property.

160M+US properties

30+API endpoints

200B+data points

API and MCPone key for both

Buy box filters and AI scores

Set the filters in one search. Every match comes back with the scores below.

Field What you get Made by Endpoint
Location A city, county or ZIP code. More than 1 at once, but not a whole state. Property records area-autocomplete
Price and property type The list price range and the kind of property. Property records run-property-search
Condition The condition our AI reads from the listing photos. AI model run-property-search
Estimated ROI and cap rate Estimated return, cap rate and cash-on-cash ranges. AI model run-property-search
Seller Motivation Score How much room the seller leaves to negotiate. AI model price-flexibility-score
List price to estimated ARV How the asking price compares with the estimated after-repair value. AI model run-property-search
Days on market and sold dates How long a listing has been up, or a sold date range. Property records run-property-search
Investment potential One score from 0 to 100 per property. AI model investment-potential
Rental returns Estimated rent, net operating income, cap rate and IRR for a 12-month lease. AI model rental-long-term
Market outlook A 0 to 100 ZIP score with 1, 3 and 6-month trends and the absorption rate. AI model market-outlook
Bulk records Up to 100 properties per page by ZIP, city or state. Property records bulk-info

How the AI ranks a market

Filters narrow the market. Our models score what is left, so the shortlist is ranked before an analyst opens it.

What the models read

  • Search areaCities, counties or ZIP codes.

  • Buy box filtersPrice, condition, returns and more.

  • Listing photosRead by the vision model.

  • Market signalsSales, inventory and days on market by ZIP.

Homesage.ai models

  • Vision condition modelScores condition from the photos.

  • Returns and rent modelsReturn estimated ROI, rent, cap rate and IRR.

  • Seller Motivation Score modelReads days on market, price changes and comps.

  • Market outlook modelClasses each ZIP from buyer’s to seller’s market.

What you get back

  • Ranked shortlistWith list price, estimated ROI and condition.

  • Investment potential0 to 100 per property.

  • Market outlook0 to 100 per ZIP, with trends.

  • Rental returnsFor hold strategies.

Scores and returns are estimates for screening. Inspect every property you shortlist.

From ZIP code to shortlist

Run the same 4 stages on every market you cover.

  1. 1

    Pick the market

    Turn a city, county or ZIP name into a search area, then read how it is moving.

    • Area autocomplete area-autocomplete

      Up to 5 matching cities, counties or ZIP codes, ready to pass into a search.

    • Market outlook market-outlook

      A 0 to 100 score that marks a ZIP code as a buyer’s, balanced or seller’s market. It also returns 1, 3 and 6-month trends.

    • Sales count by ZIP sold-count-by-zip

      The number of properties sold in a ZIP code in the last 365 days.

  2. 2

    Run the search

    Check the match count first, then pull every property.

    • Search preview preview-property-search

      The number of properties that match your filters and the credits the full search will use.

    • Property search run-property-search

      Every property that matches your filters, with list price, estimated ROI and condition.

    • Bulk property search bulk-info

      Paginated results by ZIP, city or state. Each one carries estimated ARV, estimated renovation cost, estimated ROI and a fixer-upper flag.

  3. 3

    Score each property

    Rank the shortlist before an analyst opens a single file.

    • Investment potential investment-potential

      An investment-potential score from 0 to 100.

    • Long-term rental rental-long-term

      Estimated monthly rent and net operating income for a 12-month lease. It also returns cap rate, cash-on-cash return and IRR.

    • Seller Motivation Score price-flexibility-score

      How much room a seller leaves to negotiate, based on days on market, price changes and comps. A higher score means more room.

  4. 4

    Check condition and value

    Confirm the top picks against condition, nearby sales and location.

    • Fixer-upper check needs-tlc-check

      A yes or no flag for properties likely to need major renovation.

    • Comparable sales comps

      Recent sold properties near the subject with sale price, sale date and distance. It also returns an estimated ARV.

    • Location red flags location-red-flags

      Nearby risks such as industrial sites, rail lines and power lines. It also returns a risk score for the address.

See the data before you search

These are real response shapes from our docs. The search returns your matches, and the market outlook scores the ZIP behind them.

Run the same calls from your data pipeline, or ask for them in plain English through the MCP.

Start nowBook a demo

Property searchMarket outlook

{
  "count": 1240,
  "data": [{
    "address": "",
    "list_price": 480000,
    "roi": 0.21,
    "property_condition": "outdated"
  }]
}
{
  "zip_code": "65802",
  "outlook_score": {
    "value": 70.7,
    "label": "Seller’s Market"
  },
  "market_velocity": {
    "avg_days_on_market_metro": 65
  },
  "micro_stats": {
    "active_count": 208,
    "sold_count_90d": 536
  }
}

Sample responses from the property search and market outlook docs pages, trimmed. Address hidden.

Use it where your team works

Option Best for Start here
REST API Your own software, models and data pipelines API docs, one page per endpoint
MCP server Analysts who work in Claude, ChatGPT or another AI assistant Connect the MCP in 3 steps
Investment Property Search The same search in our web app, no code Open Investment Property Search
Sage Questions in plain English inside the Homesage.ai app Meet Sage

Questions funds ask

What investment data do you cover?

Insights on 160M+ US properties. Search by city, county or ZIP code. Then filter by price, condition, returns and timing.

Can I screen a whole state?

A search takes 1 or more cities, counties or ZIP codes. Bulk records can be pulled by state, 100 per page.

How do I control cost on a big search?

Preview the match count and credit cost first. The full search charges credits for each property it returns.

Which scores come from AI models?

Condition, estimated ROI and estimated rent come from models. So do the Seller Motivation Score, investment potential and the ZIP market outlook.

Can analysts ask for a shortlist in plain English?

Connect the Homesage.ai MCP to an AI assistant. It runs the same search and scoring calls and confirms the credit cost first.

Before you start

  • Scores and returns are estimates for screening.

  • The condition score only sees what the listing photos show.

  • Coverage is the United States only.

  • A search needs a location, a status and at least 1 other filter.

  • Usage is credit-based. Plans are on the pricing page.

Other use cases

Related on Homesage.ai

Test your buy box on one market

Create an account and run a search preview on a ZIP code you know well. Or book a demo and bring your criteria.

Estimated values. Not investment advice. Sample responses come from our public API docs, read 2026-11-07.

Start nowBook a demo