v1.3.0 — 176 tests passing

Matching engine
as an API

Multi-signal compatibility scoring for dating, networking, and roommate apps. 6 weighted signals, ANN retrieval, bidirectional consent. Built in Rust — ~13ms per request.

# Get matches for a user
curl -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.matchagent.io/matches/42?n=10"

# Response
{
  "user_id": 42,
  "matches": [
    {
      "user_id": 87,
      "score": 0.847,
      "signals": {
        "values": 0.92,
        "lifestyle": 0.81,
        "personality": 0.78,
        "interests": 0.85
      },
      "coach": {
        "opener": "You both love hiking and value family...",
        "style": "warm_direct"
      }
    }
  ],
  "retrieval": "ann",
  "latency_ms": 12
}

6-Signal Scoring

Not just location + photos. Real compatibility.

Values

35%

Family, monogamy, children, faith

Lifestyle

25%

Activity level, habits, schedule

Personality

20%

Big Five (OCEAN) traits

Interests

15%

Shared hobbies and activities

Logistics

-3%

Distance penalty

Conflicts

-2%

Dealbreaker detection

Built for Production

Everything you need to ship matching that works.

~13ms Latency

ANN retrieval + full scoring pipeline in milliseconds. Built in Rust with Tokio async.

Bidirectional Consent

Score = geometric mean of both directions. No one-sided matches.

MMR Diversity

Maximal Marginal Relevance prevents showing 5 clones. Real diversity in results.

Temporal Decay

Inactive profiles automatically deprioritized. Active users surface first.

Cold Start Strategy

New profiles get exploration boost. Solve the chicken-and-egg problem.

Simple REST API

POST profiles, GET matches. JWT auth. Works with any stack in any language.

Production Pipeline

From request to ranked matches in ~13ms.

1

ANN Retrieval

pgvector finds 200 nearest candidates by embedding cosine similarity

2

Batch Profile Fetch

Single SQL query loads all candidate profiles with values, lifestyle, personality

3

Multi-Signal Scoring

6 weighted signals computed for each candidate pair (bidirectional)

4

Feedback Loop

Past interactions (likes, passes, ghosts) adjust scores up or down

5

Temporal Decay + Cold Start

Inactive users deprioritized, new users get exploration boost

6

MMR Reranking

Maximal Marginal Relevance ensures diversity — no 5 clones

7

Coach + Energy

Personalized openers and energy compatibility (introvert/extrovert 4D)

Who Uses MatchAgent

Dating Apps

Replace ELO + location with real compatibility. Values, personality, lifestyle — not just photos.

Professional Networking

Match co-founders, mentors, and collaborators by work style, values, and complementary skills.

Roommate / Coliving

Lifestyle compatibility scoring — sleep schedule, cleanliness, social habits.

Friendship Apps

The pipeline supports relationship_goal: friendship. Same signals, different context.

Simple Pricing

Pay for matches, not seats. Scale as you grow.

Starter

For MVPs and early-stage apps

$49/month
10,000 matches/month
  • 6-signal weighted scoring
  • REST API access
  • Bidirectional consent
  • JSON responses
  • Email support
Most Popular

Growth

For scaling dating and networking apps

$199/month
100,000 matches/month
  • Everything in Starter
  • ANN retrieval (pgvector)
  • MMR diversity reranking
  • Custom signal weights
  • Feedback loop integration
  • Priority support

Enterprise

For platforms with serious traffic

$499/month
Unlimited matches/month
  • Everything in Growth
  • Social Coach API
  • Energy Matching (4D)
  • Dedicated instance
  • SLA 99.9%
  • Slack support channel
  • Custom integrations

Ready to ship real matching?

Stop building matching from scratch. Integrate in hours, not months.