One Spark engine.
Embeddable and distributed.

1 · In-process Python no daemon · DuckDB-shaped

# pip install sparkrust
import sparkrust

con = sparkrust.connect()
con.sql("CREATE VIEW sales AS SELECT * FROM read_parquet('sales/*.parquet')")
df = con.sql("SELECT region, SUM(revenue) AS rev FROM sales GROUP BY region")

df.show()        # PySpark-style tabular print
rows = df.collect()   # list of tuples
table = df.arrow()   # pyarrow.Table (zero-copy ready)
pdf = df.toPandas()   # pandas DataFrame

2 · Single-node Spark Connect server laptop-scale

# same spark-connect-server binary, run locally
import pyspark.sql
spark = pyspark.sql.SparkSession.builder.remote("sc://localhost:50051").getOrCreate()

df = spark.read.parquet("s3://my-bucket/sales/")
df.groupBy("region").agg({"revenue": "sum"}).show()

3 · Distributed Spark Connect cluster same code, point at a driver

# identical pipeline, now executed across N executors
spark = pyspark.sql.SparkSession.builder.remote("sc://driver.example.com:50051").getOrCreate()

4 · In-browser WebAssembly zero install · runs in the tab

// same SQL core compiled to wasm32, loaded in a Web Worker
import init, { run_sql_json } from "./pkg/spark_wasm.js";
await init();   // fetch + instantiate the .wasm engine

const rows = '[{"region":"west","revenue":10},{"region":"west","revenue":5}]';
const out = run_sql_json(
  "SELECT region, SUM(revenue) AS rev FROM data GROUP BY region", rows);
// no server, no network — your data never leaves the tab