Operational Data Lakehouse | Spice AI

Operational Data Lakehouse

Serve real-time data and AI from object storage

Retain the scalability of object storage and the governance of open table formats. Add Spice to federate, accelerate, and power operational and AI workloads with millisecond query performance.

Get a demo View the docs

Do more with your data

Lakehouses weren't built for operational workloads

Traditional data lakehouses handle analytics well but lag for modern apps and AI agents that need sub-second responses and federated access. The result is slow queries, complex pipelines, and high costs when serving real-time operational data.

Turn your lakehouse into an operational data layer

Make your data lakehouse fast, federated, and AI-ready-serving live workloads at millisecond latency.

Federate across sources

Query databases, APIs, and object storage using standard SQL. Combine transactional and analytical data in a single query with zero ETL.

Explore SQL federation and acceleration

Accelerate object storage performance

Use data accelerators like Spice Cayenne, DuckDB, or SQLite to materialize and cache hot datasets locally. Reduce query latency from seconds to milliseconds while maintaining the scale and economics of object storage.

Explore Spice Cayenne Data Accelerator

Serve operational and AI workloads

SQL federation, acceleration, and AI inference in one runtime means you can support disparate workloads directly from your data lakehouse, all in real time.

Explore LLM inference in Spice

Native open table format support

Connect to Apache Iceberg, Delta Lake, or Parquet for schema management, ACID transactions, and optimized query planning.

Read about Apache Iceberg at Spice AI

Why enterprises operationalize their lakehouse with Spice

Spice bridges the gap between analytical and operational workloads. Combine federation, acceleration, and AI in one lightweight, portable runtime.

SQL-First Hybrid Search

Bring hybrid search - keyword, full-text, and vector - directly to your lakehouse to surface insights and relationships using simple SQL.

Mixed Workload Execution

Serve both operational applications and analytical queries from one runtime.

Open Table Support

Built-in support for Iceberg, Delta Lake, and Parquet for structured governance.

Reliability and Continuity

Failover to object storage if local acceleration is unavailable.

Governance and Observability

Enterprise access control, metrics, and auditability included.

Deployment Flexibility

Run Spice anywhere: as a sidecar, microservice, cluster, or on the managed Spice Cloud Platform.

Proven in production

Run data-intensive workloads on a high-performance engine trusted by teams building real-time systems at scale.

Testimonials

“Spice opened the door to take these critical control-plane datasets and move them next to our services in the runtime path.”

Peter Janovsky
Software Architect, Twilio

“It just spins up and works, which is really nice. The responsiveness is amazing, which is a huge gain for the customer.”

Darin Douglass
Principal Software Engineer, Barracuda

“Partnering with Spice AI has transformed how NRC Health delivers AI-driven insights. By unifying siloed data across systems, we accelerated AI feature development, reducing time-to-market from months to weeks - and sometimes days. With predictable costs and faster innovation, Spice isn't just solving some of our data and AI challenges - it's helping us redefine personalized healthcare.”

Tim Ottersburg
VP of Technology, NRC Health

Use Spice as an operational data lakehouse

Guides and examples to learn more about building an operational data lakehouse with Spice.

Blog

Making Object Storage Operational for Real-Time and AI Workloads
TLDR Introduction Although legacy systems and workflows remain common, many enterprises are re-evaluating their architectures to meet new demands – driven in part, but not exclusively, by AI – that require support for more data-intensive and real-time applications. The underlying storage needs for these novel workloads are generally outside the bounds of a traditional operational

Read more

Recipe

Federated SQL Query Cookbook
Learn how to fetch combined data from S3 Parquet, PostgreSQL, and Dremio in a single query.

View Cookbook

Data Acceleration with DuckDB
This recipe walks through how to accelerate a local copy of the taxi trips dataset stored in S3 using DuckDB as the data accelerator engine.

View Recipe

See Spice in action

Walk through your use case with an engineer and see how Spice handles federation, acceleration, and AI integration for production workloads.

Talk to an engineer