9.47M records/sec • 12x faster than TimescaleDB • Portable Parquet storage

Built for Billion-Record
Industrial Workloads

Racing telemetry. Smart cities. Mining sensors. Medical devices.

When you have billions of sensor readings and milliseconds matter, Arc delivers.

Get started in seconds

docker run -d -p 8000:8000 \
  -e STORAGE_BACKEND=local \
  -v arc-data:/app/data \
  ghcr.io/basekick-labs/arc:latest

Single binary. No dependencies. Production-ready in minutes.

Join Arc Cloud Waitlist →

Read the Docs →

Industrial IoT Generates Massive Data

100M+ sensor readings in a single race. 10B infrastructure events daily in a smart city.

Traditional time-series databases can't keep up. Arc can.

Real Industrial IoT Scale:

🏎️

Race telemetry: 100M+ sensor readings in 3 hours

🏙️

Smart city: 10B infrastructure sensor events daily

⚙️

Mining operation: Billions of equipment telemetry points

🏥

Medical devices: Real-time patient monitoring at scale

Built for billion-record workloads.

Why Arc

DuckDB SQL. No Proprietary Query Language.

Not a custom DSL. Not a query language that changes every major version.

Not vendor lock-in through proprietary syntax.

Just DuckDB-powered SQL with window functions, CTEs, and joins.

Analyze equipment anomalies across facilities

Correlate temperature, pressure, and vibration sensors

SELECT
  device_id,
  facility_name,
  AVG(temperature) OVER (
    PARTITION BY device_id
    ORDER BY timestamp
    ROWS BETWEEN 10 PRECEDING AND CURRENT ROW
  ) as temp_moving_avg,
  MAX(pressure) as peak_pressure,
  STDDEV(vibration) as vibration_variance
FROM iot_sensors
WHERE timestamp > NOW() - INTERVAL '24 hours'
  AND facility_id IN ('mining_site_42', 'plant_7')
GROUP BY device_id, facility_name, timestamp
HAVING MAX(pressure) > 850 OR STDDEV(vibration) > 2.5;

If you know SQL, you know Arc. Powered by DuckDB.

Window Functions

Moving averages, ranking, and complex aggregations built-in

CTEs & Subqueries

Break down complex analysis into readable, composable parts

JOINs Across Sensors

Correlate temperature, pressure, vibration data across devices

Parquet files you actually own

Your data lives in standard Parquet files on S3, MinIO, or local disk.

Arc disappears tomorrow? You still own your data.

Query it with DuckDB, ClickHouse, Snowflake, or any tool that reads Parquet.

Zero proprietary formats. Zero lock-in.

This is what "portable data" actually means.

S3 / MinIO / Local

Store anywhere you want

Standard Parquet

Industry standard format

You Own It

No vendor lock-in, ever

Performance

9.47M records/sec sustained

High-throughput metrics ingestion via MessagePack columnar format.

No degradation. No memory leaks. Just stable performance.

9.47M

records/sec

sustained throughput over 60 seconds

Hardware: M3 Max 14-core, 36GB RAM • Workers: 35 • Duration: 60 seconds • Success rate: 100%

p50: 2.79ms • p95: 4.66ms • p99: 6.11ms

See Arc in Action

Live demos running on Arc. Real data, real-time ingestion, sub-second queries. All powered by Arc's high-performance time-series engine.

Live

🚢 Vessel Tracking

Real-time AIS data from vessels in Singapore's Strait of Malacca. Live position updates every 30 seconds.

✈️ Flight Tracking

Live ADS-B data tracking aircraft over New York City. Real-time altitude, speed, and position updates.

🌦️ Weather Tracking

Multi-city weather monitoring across Buenos Aires, London, and Tokyo. Temperature, humidity, and pressure trends.

Data: 3 cities

Source: OpenWeatherMap

→

Live

📊 System Monitoring

Real-time Docker container metrics for the Arc database. CPU, memory, network, and disk I/O tracking.

Built for Migration

Migrate from your existing time-series database

We help with migration at no cost.

Arc speaks InfluxDB Line Protocol natively.

Point Telegraf at Arc. Dual-write during migration. Cut over when ready.

No agent changes. No downtime. No data loss.

Multiple InfluxDB 1.x Enterprise customers already testing migration

Already running TimescaleDB?

We'll help you migrate at no cost.

Keep your SQL queries. Arc uses standard DuckDB SQL with window functions, CTEs, and joins.

Own your data in Parquet. No vendor lock-in. Query with any tool. 10-50x faster queries after compaction.

Already running QuestDB?

We'll help you migrate at no cost.

Broader SQL support. Full window functions, CTEs, complex joins - features QuestDB doesn't support.

Better ecosystem integration. Native Grafana datasource, VSCode extension, Apache Superset dialect.

Features That Matter for IoT

Grafana Integration

Official Grafana datasource plugin. Build dashboards for sensor data, equipment telemetry, and facility monitoring. Azure AD OAuth support.

Setup guide →

VSCode Extension

Full-featured database manager. Query editor with autocomplete. Notebooks for analysis. CSV import. Alerting.

Install from marketplace →

Automatic Compaction

Small files merge into optimized 512MB Parquet files. 10-50x faster queries with zero configuration.

Retention Policies

Time-based lifecycle management. Keep 7 days of raw data, 90 days of rollups, 2 years of aggregates.

Or keep everything forever - storage is cheap.

GDPR-Compliant Deletion

Precise record deletion with file rewrites. No tombstones. No query overhead.

Write-Ahead Log (WAL)

Optional durability for zero data loss. Disabled by default for maximum throughput.

Enable when durability matters more than speed.

Multi-Database Architecture

Organize by facility, device type, or environment. Isolated namespaces for multi-tenant deployments. Query across databases with standard SQL joins.

Apache Superset Integration

Native dialect for BI dashboards. Connect your existing visualization tools.

See all features →

Trusted by Industrial Teams

Environmental Monitoring - Migrated from TimescaleDB. 10x faster queries on CO2 sensor data from vehicle-mounted devices.

Fleet Tracking - Processing billions of GPS tracking events. Arc handles their scale effortlessly.

Clinical IoT - Real-time patient monitoring across multiple facilities. Arc delivers the performance they need.

12.3B

rows in production

and counting

9.47M

records/sec

sustained throughput

Read case studies →

FAQ

Yes. Version 25.12.1 is stable and ready for production use.

Self-hosted Arc is production-ready now.

Cloud managed version launching Q1 2026.

ClickHouse wins on raw analytical performance.

Arc wins on operational simplicity and data portability.

•ClickHouse is a distributed system requiring cluster management.
•Arc runs on a single node with object storage (S3/MinIO).
•ClickHouse uses proprietary MergeTree format.
•Arc uses standard Parquet files.

•12x faster ingestion via MessagePack columnar protocol vs InfluxDB Line Protocol.
•Portable Parquet files vs proprietary TSM format. Query with any tool.
•Standard SQL vs Flux (which InfluxData deprecated).
•InfluxDB 1.x Enterprise customers are stuck on deprecated software. Arc provides a migration path with Line Protocol compatibility.

•Parquet compression gives 3-5x reduction vs raw sensor data.
•S3 storage costs ~$0.023/GB/month.
•1TB of sensor data = ~$23/month in storage.
•Significantly cheaper than proprietary IoT platforms.
•Built-in retention policies automatically delete old data.
•Or keep everything - storage is cheap, queries are fast.

Single-node architecture currently.

HA and clustering planned for 6-12 month timeline.

For now: Run primary + standby with object storage replication.

WAL enabled for zero data loss during failover.

Currently API token authentication.

Grafana integration supports Azure AD OAuth.

RBAC, SSO, and multi-tenancy planned for enterprise release.

1Point Telegraf at Arc (Line Protocol compatible)
2Dual-write to both systems during transition
3Verify data in Arc matches InfluxDB
4Update Grafana dashboards to Arc data source
5Cut over when ready

Migration tooling and documentation: Migration guide →

Pricing

Self-Hosted

FreeForever

AGPL-3.0 open source

Run on Docker, Kubernetes, or bare metal
Local filesystem, MinIO, S3, GCS, or any S3-compatible storage
All features included
Community support

Installation guide →View on GitHub →

Coming Q1 2026

Arc Cloud

$500/month

Managed hosting with automatic backups, monitoring, and support.

Automatic backups and disaster recovery
High availability and clustering
Monitoring and alerting
Dedicated support

Early access for industrial IoT customers.

Join the waitlist →

Get Started

Self-Hosted Installation

# Docker (easiest)

docker run -d -p 8000:8000 \
  -e STORAGE_BACKEND=local \
  -v arc-data:/app/data \
  ghcr.io/basekick-labs/arc:latest

# Send data (InfluxDB Line Protocol)

curl -X POST http://localhost:8000/api/v1/write/line-protocol \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: text/plain" \
  -H "x-arc-database: default" \
  --data-binary "cpu,host=server01 value=0.64 1633024800000000000"

# Or MessagePack Columnar (2.55x faster)

echo '{"m":"cpu","columns":{"time":[1633024800000],"host":["server01"],"usage":[95.0]}}' | \
python3 -c "import sys,msgpack,json; sys.stdout.buffer.write(msgpack.packb(json.load(sys.stdin)))" | \
curl -X POST http://localhost:8000/api/v1/write/msgpack \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/msgpack" \
  -H "x-arc-database: default" \
  --data-binary @-

# Query with SQL

curl -X POST http://localhost:8000/api/v1/query \
  -H "Authorization: Bearer YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -H "x-arc-database: default" \
  -d '{"sql":"SELECT * FROM cpu WHERE time > NOW() - INTERVAL 1 HOUR","format":"json"}'

Full installation guide →GitHub repository →

Arc Cloud Waitlist

Join the waitlist for managed hosting.

Early access members get preferential pricing.

Ready to handle billion-record sensor workloads?

Join Arc Cloud Waitlist →Install Self-Hosted →

Built for Billion-RecordIndustrial Workloads

Industrial IoT Generates Massive Data

Real Industrial IoT Scale:

DuckDB SQL. No Proprietary Query Language.

Window Functions

CTEs & Subqueries

JOINs Across Sensors

Parquet files you actually own

S3 / MinIO / Local

Standard Parquet

You Own It

9.47M records/sec sustained

See Arc in Action

🚢 Vessel Tracking

✈️ Flight Tracking

🌦️ Weather Tracking

📊 System Monitoring

Migrate from your existing time-series database

Arc speaks InfluxDB Line Protocol natively.

Already running TimescaleDB?

Already running QuestDB?

Features That Matter for IoT

Grafana Integration

VSCode Extension

Automatic Compaction

Retention Policies

GDPR-Compliant Deletion

Write-Ahead Log (WAL)

Multi-Database Architecture

Apache Superset Integration

Trusted by Industrial Teams

FAQ

Pricing

Self-Hosted

Arc Cloud

Get Started

Self-Hosted Installation

Arc Cloud Waitlist

Ready to handle billion-record sensor workloads?

Built for Billion-Record
Industrial Workloads