- Home
- Data Lakehouse Platforms
- LavaLake
LavaLake
What it is
LavaLake combines a data warehouse and lakehouse with SQL, dashboards, and AI agents, designed for deployment in a customer's own data center. Its assistant can find data, query metrics, and create dashboards using the signed-in user's permissions. An included MCP server lets external agents use platform tools under those permissions. Read-only database sources include PostgreSQL, MySQL, MS SQL Server, SAP Business One, and SAP S/4HANA. CSV and DATEV imports are supported, while PDF, Word, and text documents can be searched. Hybrid search combines vector and keyword results using a locally run nomic-embed-text model with PostgreSQL and pgvector. The lakehouse uses Apache Iceberg on S3-compatible storage, Nessie as a versioned catalog, and Trino as its query engine. Tableau and Power BI can connect through a read-only HTTP feed that applies analyst identity and records data fetches in an audit chain. The maker says lakehouse data and local search stay on the customer's network, while external AI providers receive conversation content and assistant tool results. Core is free with no time limit, on one machine and up to 16 vCPU; Team is €249 a month.
For and against
For
- Core has no time limit.
- Assistant actions use the signed-in user's permissions.
- Supports Apache Iceberg with Trino.
- Tableau and Power BI have a read-only feed.
Against
- High availability is planned, not listed as available.
- Fully air-gapped operation is planned.
- Change data capture and continuous ingestion are in development.
- External AI providers receive conversation content and tool results.
The verdict
LavaLake combines data storage, search, analytics, and assistant tools for deployment in a customer's data center. Its planned capabilities and external AI data handling are important considerations.
Who it suits
LavaLake may suit organizations seeking an on-premises data platform with SQL, dashboards, and permission-aware AI tools. Teams using external AI providers should consider what conversation content and assistant tool results are sent to them.
Plans and prices
Core
Up to 16 vCPU · single machine · community support
Read 7 Oct 2026 · lavalake.io
Team
Up to 192 vCPU · up to 10 users · ticket support, answer within a business day
Read 7 Oct 2026 · lavalake.io
Business
Up to 512 vCPU · unlimited users · 8/5 support with a committed response time
Read 7 Oct 2026 · lavalake.io
Enterprise
Unlimited vCPU · unlimited users · named contact · migration support included
Read 7 Oct 2026 · lavalake.io
On the record
- Access controls
- The security design uses Keycloak OIDC, RFC 8693 token exchange, Trino-enforced row access and column masking, and a WORM hash-chain audit log.lavalake.io · read 7 Oct 2026
- AI assistant
- Its built-in assistant can find data, query metrics, and create dashboards, with actions running under the signed-in user's permissions.lavalake.io · read 7 Oct 2026
- AI data handling
- The maker says the lakehouse and local search stay on the customer's network, while external AI providers receive conversation content and assistant tool results.lavalake.io · read 7 Oct 2026
- BI integrations
- A read-only HTTP feed supports Tableau and Power BI, applying the analyst's identity and recording data fetches in the audit chain.lavalake.io · read 7 Oct 2026
- Data sources
- The product lists PostgreSQL, MySQL, MS SQL Server, SAP Business One, and SAP S/4HANA as read-only database sources.lavalake.io · read 7 Oct 2026
- Deployment
- The reference deployment is a Docker Compose stack on one machine, with Ansible installation for Debian/Ubuntu; the Kubernetes Helm path has operational gaps including policy integration.lavalake.io · read 7 Oct 2026
- Files and documents
- It supports CSV and DATEV file imports and makes PDF, Word, and text documents searchable.lavalake.io · read 7 Oct 2026
- MCP
- The platform includes an MCP server that lets external agents use platform tools under the user's permissions.lavalake.io · read 7 Oct 2026
- Notable limitations
- High availability and fully air-gapped operation are listed as planned, and change data capture and continuous ingestion are in development.lavalake.io · read 7 Oct 2026
- Purpose
- LavaLake combines a data warehouse and lakehouse with AI agents, SQL, and dashboards for deployment in a customer's own data center.lavalake.io · read 7 Oct 2026
- Search
- Hybrid search combines vector and keyword results using a locally run nomic-embed-text model and PostgreSQL with pgvector.lavalake.io · read 7 Oct 2026
- Storage and formats
- The lakehouse uses Apache Iceberg on S3-compatible storage with Nessie as its versioned catalog and Trino as its query engine.lavalake.io · read 7 Oct 2026
