New in Spice: Faster point lookups, Cayenne indexes, and clustering across storage tiers. Read the September update.
Product
Analytics Replica
Add a real-time analytics replica to your operational database, without ETL
SQL Federation & Acceleration
Query across operational and analytical data sources with local acceleration
Hybrid SQL Search
Combine vector similarity, full-text, and keyword search in a single SQL query
LLM Inference
Call local or hosted LLMs from the Spice query engine
Secure AI Sandboxing
Safely connect AI to enterprise data
AI Model Serving
Serve, evaluate, and ground AI models in the context of your data
Edge to Cloud Deployments
Deploy Spice anywhere
Real-Time Change Data Capture
Sync accelerated datasets with real-time changes
Distributed Query
Scale beyond single-node limits
MCP Server & Gateway
Run MCP servers locally or over SSE
Solutions
Analytics
Real-time analytics on operational data, without ETL
Application Search
Context-aware, hybrid search for apps
Datalake Accelerator
Up to 100x faster queries
Operational Data Lakehouse
Power operational and analytical workloads from your datalake
Secure AI Agents
Deploy secure, scalable AI agents
Retrieval-Augmented Generation
Build more accurate and trustworthy RAG systems
Cybersecurity
Data and AI foundation for modern security solutions
Financial Services
Unify real-time, governed financial data
SaaS
Deliver responsive, personalized, and secure SaaS apps
Pricing
Resources
Blog
Product updates, customer stories, and technical guides
Integrations
Integrations with databases, data warehouses, data lakes, and more
Quick Starts
Get started in minutes
Cookbook
Find ready-to-use examples
Cloud Docs
Documentation for the Spice Cloud Platform
Open Source Docs
Documentation for Spice OSS
Company
About Us
Powering the next generation of applications
Careers
Build the future of data and AI
Connect to 40+ data sources
Security
Security you can trust
Contact Us
Get in touch with the Spice AI team
Submit application