EMATIX(R) DATA TERMINAL — ROBCO INDUSTRIES UNIFIED OPERATING SYSTEM
COPYRIGHT 2026 EMATIX SYSTEMS — ALL RIGHTS RESERVED
USER: GUEST   SESSION: 2026-05-20 19:38:15Z   HOST: ematix.dev/terminal

DECLARATIVE PYTHON DATA PIPELINES.

Rust + Apache Arrow under the hood. Move data between databases, files, and streams with one decorator. Cron schedules, DAG dependencies, watermarks, schema evolution, restart-safe state, at-least-once delivery — built in. No extra scheduler service to deploy.

> pip install ematix-flow
SELECT TERMINAL
// 01

User Guide

Install, connections, pipelines, modes, scheduling, streaming, stream processing, CLI. Each chapter is a copy-paste-runnable example.

▶ ENTER /guide
// 02

Specs & Benchmarks

Why ematix-flow exists, what's shipped, TPC-H numbers (1.69× DuckDB, 2.71× Polars, 12.9× PySpark geomean), and how it stacks up against the field.

▶ ENTER /specs
QUICK PEEK
// example: postgres → managed table on a 5-min cron
from ematix_flow import ematix, ManagedTable, Annotated, BigInt, Text, TimestampTZ, pk

@ematix.connection
class warehouse:
    kind = "postgres"
    url = "${WAREHOUSE_URL}"

class Events(ManagedTable):
    __schema__ = "analytics"
    __tablename__ = "events"

    event_id: Annotated[BigInt, pk()]
    name: Text | None
    received_at: TimestampTZ

@ematix.pipeline(
    target=Events,
    target_connection="warehouse",
    schedule="*/5 * * * *",
    mode="append",
)
def ingest_events(conn):
    return "SELECT event_id, name, received_at FROM raw.events"
● Status: v0.3.0 on PyPI — all four surfaces stable.