Microsecond Inference &
Horizontal Scalability
All Inside Your Database

Get lightning speed feature recall for online predictions, along with instant scalability and long term monitoring for your machine learning models running inside the world’s most capable feature store.

PostgresML Demo

How It
Works

PostgresML integrates the feature store, model store and inference layers into a seamless shared memory space.

Implemented inside PostgreSQL with Rust, it safely achieves maximum performance, eliminating network calls, process boundaries, data duplication and (de)serialization required in traditional machine learning architectures.

Try Now For Free
Performance icon

Fast

Up to 40x performance improvement over traditional machine learning architectures.

Performance icon

Comprehensive

PostgresML is your model store, feature store, inference server and deployment pipeline.

Performance icon

Simple

Say good bye to Python microservices. PostgresML trains and manages your machine learning models end to end.

Performance icon

Scalable

Scale your inference layer to millions of predictions per second with PostgresML replicas.

Performance icon

Your Data

Automatically add your features with replication from your primary data store, via our secure connection manager.

Performance icon

Highly Available

Abstract everything behind a single connection string with smart query routing, sharding, and enterprise-grade managed infrastructure.

How to Use It

Train icon

Train


SELECT pgml.train(
  'Sales Forecasting',
  task => 'regression',
  relation_name => 'historical_sales',
  y_column_name => 'next_week_sales',
  algorithm => 'xgboost'
);
            
Deploy icon

Deploy


SELECT pgml.deploy(
  'Sales Forecasting',
  strategy => 'best_score',
  algorithm => 'xgboost'
);
              
Predict icon

Predict


SELECT pgml.predict(
  'Sales Forecasting',
  ARRAY[
    last_week_sales,
    week_of_year
  ]
) AS prediction
ORDER BY prediction DESC;
            

What Adopters Say

Quote icon

"Absolutely brilliant" on PgCat, our sharded PostgreSQL proxy.

Carnegie Mellon
Quote icon

"The improvement is quite remarkable" on PostgresML v2.0.

Scaling Postgres
Quote icon

"Bleeding edge stuff in a matter of minutes."

Hasura
Quote icon

"I'm itching to apply it everywhere I set my foot!"

Stone Cross Foundation
Quote icon

"The simplicity and ergonomics are really exciting."

Practical AI
Rotating cube Rotating cube

Start Now
With Machine Learning

Get Started For Free
Product features

Discover All Features

Feature icon

Fastest Inference

PostgresML eliminates separation between your model server and your feature store, minimizing latency and computation costs. Our benchmarks show a 8x-40x improvement over Python HTTP microservices.

Feature icon

All Your Favorite Algorithms

Whether you need a simple linear regression or extreme gradient boosting, PostgresML includes support for all classification and regression algorithms in Scikit Learn, XGBoost, LightGBM and pre-trained deep learning models from Hugging Face.

Feature icon

Hyperparameter Search

Use either grid or random searches with cross validation on your training data to discover the most important knobs to tweak on your favorite algorithm, with best practices automatically enforced for testing model quality before deploying to production.

Feature icon

Online & Offline

Predictions are served via a standard Postgres connection to ensure that your core apps can always access both your data and your models in real time. Pure SQL workflows also enable batch predictions to cache results in native Postgres tables.

47

Algorithms

<1 ms

Prediction Latency

8x-40x

Faster than Python

1M+

QPS on EC2

We Have the Perfect
Plan For You

Free tier icon

Free

Free tier full of features for hobbyists.

$0

Features

  • Checkmark Open Source PostgresML with 47 machine learning algorithms
  • Checkmark Automatic data preprocessing for building optimal models
  • Checkmark 5 GiB of disk space
  • Checkmark Web Dashboard
  • Checkmark PostgreSQL database to integrate with your apps
  • Checkmark Hangout with us in Discord
Free tier icon

Business

Empower your machine learning operations.

Starting at $0.18/h

Features

  • Checkmark Dedicated high performance hardware
  • Checkmark Up to 16 TiB of disk space
  • Checkmark Horizontally scalable inference with replicas
  • Checkmark High availability for your production applications
  • Checkmark Backups
  • Checkmark Dedicated support
Free tier icon

Enterprise

Tailored solutions for your enterprise.

Contact Us

Features

  • Checkmark Everything in the Business Tier
  • Checkmark Cloud Prem
  • Checkmark Premium support and dedicated TAM
  • Checkmark Influence on the roadmap
Powered by PostgresML Logo PostgresML