Get the latest insights
Product updates, developer guides, use cases, and more.
Barracuda Networks Gains 100x Faster Query Responses and 50% Reduction in Operational Costs with Spice.ai OSS
Barracuda Networks used Spice.ai OSS to accelerate Delta Lake and audit log queries by up to 100x while cutting operational costs by 50% for archival access.
Building an Enterprise SRE Agent with OpenClaw and Spice
Learn how Spice gives OpenClaw-style enterprise AI agents safe, governed, and observable access to production data without exposing source system credentials.
AWS Workshop: Federated Queries and Hybrid Search with Spice.ai
Deploy Spice as a unified data and AI substrate on AWS. The workshop covers federated SQL, hybrid search, and LLM inference with Aurora, S3, and Bedrock.
Localhost Latency at Scale: The Spice Cluster-Sidecar Architecture
How the Spice cluster-sidecar architecture gives applications, services, and AI agents sandboxed, localhost-latency query, search, and inference at scale.
Spice Cloud v2.0-rc.2: Cayenne RC, ADBC BigQuery, and Catalog Connectors
Spice Cloud v2.0-rc.2 adds Spice Cayenne RC, ADBC with BigQuery support, new catalog connectors, and major portal and developer workflow improvements.
Multi-Tenancy for AI Agents without the Pipelines
Serve multi-tenant AI agents from disparate enterprise data sources with tenant isolation, federated SQL, and CDC acceleration without per-tenant pipelines.
Apache Ballista at Spice AI: Distributed Query Execution Without the Operational Tax
Learn how Spice AI integrates Apache Ballista for distributed query execution with multi-active schedulers, fault-tolerant shuffle, and horizontal scaling.
Vortex at Spice AI: The Columnar Format for Data-Intensive Workloads
Learn how Spice AI uses the Vortex columnar format in Cayenne to speed data-intensive workloads, reduce memory use, and scale concurrent ingestion and queries.
Introducing Spice Skills for AI Agents
Spice Skills gives AI coding agents -- Claude Code, Cursor, and others -- packaged instructions for setting up, configuring, and working with Spice.ai OSS.
Apache Iceberg at Spice AI: How we Query, Accelerate, and Write to Open Table Formats
How Spice AI integrates Apache Iceberg: zero-ETL federated queries, sub-second acceleration of hot datasets, and ACID-compliant writes to open table formats.
A Developer's Guide to Understanding Spice.ai
Learn what Spice.ai is, when to use it, and how it solves enterprise data challenges. A developer-focused guide to federation, acceleration, search, and AI.
Operationalizing Amazon S3 for AI: From Data Lake to AI-Ready Platform in Minutes
Transform Amazon S3 from passive storage into an AI-ready platform with Spice. A real-world example covering ingestion, hybrid search, and LLM inference.
Most popular
Deep dives and guides readers return to most, from SQL federation to hybrid search.
Getting Started with Spice.ai SQL Query Federation & Acceleration
Get started with Spice.ai SQL query federation and acceleration: query databases, warehouses, and lakes through one SQL interface with sub-second results.
How we use Apache DataFusion at Spice AI
How Spice extends Apache DataFusion with custom table providers, optimizer rules, and UDFs to power federated SQL, hybrid search, and AI inference at scale.
True Hybrid Search: Vector, Full-Text, and SQL in One Runtime
Build hybrid search without managing multiple systems. Spice combines vector similarity, full-text search, and SQL filters in one open-source runtime.
Real-Time Hybrid Search Using RRF: A Hands-On Guide with Spice
Build real-time hybrid search with Reciprocal Rank Fusion (RRF) in SQL using Spice, combining keyword, vector, and time-based relevance in a single query.
Spice AI achieves SOC 2 Type II compliance
Spice AI achieves SOC 2 Type II compliance as of February 2024, demonstrating enterprise-grade security controls for its data and AI infrastructure platform.
Spice Firecache | Cloud-Scale DuckDB
Spice Firecache is a real-time, in-memory SQL service built on cloud-scale DuckDB, delivering fast materialized views of web3 data for modern applications.
