kibae/pg_onnx

pg_onnx: ONNX Runtime integrated with PostgreSQL. Perform ML inference with data in your database.

42
/ 100
Emerging

This tool helps data professionals integrate machine learning predictions directly into their PostgreSQL databases. You can upload pre-trained ONNX models, and then use SQL queries to perform real-time inference on data stored within your tables. This is ideal for data scientists, machine learning engineers, and database administrators who want to operationalize ML models efficiently.

Use this if you need to run machine learning predictions directly within your PostgreSQL database using your existing data, without moving it to external services.

Not ideal if you need to train machine learning models or require extremely low-latency inference on very high-volume, real-time streaming data outside of a database context.

database-analytics machine-learning-operations data-warehousing real-time-predictions SQL-ML
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

58

Forks

4

Language

C++

License

MIT

Last pushed

Mar 06, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kibae/pg_onnx"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.