Cube vs Sema
Cube
cube.devSema
semalayer.comSide by side
| Figure | Cube | Sema |
|---|---|---|
| Price from | $40/mo | $49/mo |
| Free plan | Yes | Yes |
| Free trial | — | Yes |
| Open source | Yes | — |
| Web | Yes | Yes |
| Linux | Yes | — |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 4 | 4 |
| Spec score · Semantic Layer Software | 9.3 (#1) | 8.7 (#4) |
| Company | The company is Cube Dev, Inc.; its about page names Artyom Keydunov and Pavel Tiunov as co-founders. | Sema says it was founded in 2025 and is remote-first. |
| Compliance | Cube Cloud states SOC 2 Type II, HIPAA and GDPR compliance and offers audit logs across deployments. | Sema’s trust page says SOC 2 Type II is in progress, GDPR-ready data processing terms are available, and HIPAA support with a BAA is available for eligible plans on request. |
| Deployment | Cube Cloud can run as a managed multi-tenant service on AWS or GCP, in a VPC on AWS, GCP, or Azure, or on a customer's cloud through BYOC. | Sema says it can run in the customer’s VPC or its own environment; its self-hosted Kubernetes deployment uses a Helm chart and customer-provided Postgres and object storage. |
| Founded | 2019 | 2025 |
| Integrations | Listed data sources include Snowflake, BigQuery, Redshift, Databricks, ClickHouse, PostgreSQL, MySQL, MongoDB, Trino, Presto and AWS Athena. | Sema describes its capabilities as MCP tools for use with Claude, Cursor, or an in-house agent, and supports OAuth2/OIDC identity providers including Okta, Entra, Auth0, and Google Workspace. |
| Product | Cube is an agentic analytics platform built on a semantic layer for business users and AI agents. | Sema is a semantic layer for enterprise AI that connects databases, infers data meaning, and answers business questions in plain English with governance. |
| Security | Cube states that data is encrypted at rest, API access uses token-based security, and application traffic is encrypted over SSL/TLS 1.2. | Sema says it uses TLS in transit and encryption at rest, role-based access, restricted-column masking, workspace isolation, and an append-only log of queries, plans, and configuration changes. |
| Self-hosting | Cube Core is distributed as Docker images and can run on a customer's own infrastructure. | The architecture describes Kubernetes deployment with a Helm chart, customer-provided PostgreSQL and object storage, and a control plane that holds the graph rather than warehouse rows. |
| Support | Cube lists community support for Free, limited chat and email for Starter, and chat and email plus a dedicated CSM for Enterprise. | The Pro plan includes email support, Business includes priority support, and Enterprise includes a named customer success manager. |
Plans
In their own words
Cube
Cube is an analytics platform with a semantic layer that encodes governed business definitions for dashboards, embedded applications, and AI agents. Cube Cloud supports internal business intelligence and embedded analytics, while Cube Core is the open-source project alongside which the cloud platform is built. The Free plan includes a semantic layer IDE, workbooks, dashboard publishing, semantic model and workbook agents, and analytics chat. Listed data sources include PostgreSQL, Snowflake, ClickHouse, Databricks, BigQuery, MySQL, Oracle, Redshift, MongoDB, and Trino; integrations include dbt, Dagster, Prefect, Airflow, and Coalesce.io. Cube Core processes API requests using pre-aggregated data in Cube Store or raw data in connected databases. Cloud deployment options include a managed multi-tenant service on AWS or GCP, a VPC on AWS, GCP, or Azure, and a customer's cloud through BYOC. Cube lists a free plan, Starter at $40 a month per developer, and Premium at $80 a month per developer.
Sema
Sema is a semantic layer for enterprise AI that connects databases and answers business questions in plain English, with governance controls. It maps tables, joins, metrics, and business terms into a typed graph; verified inferred joins can be reused in later answers. It can ask clarifying questions, show the SQL and graph nodes behind an answer, and select a chart. Users can save and schedule reports for email delivery and set metric alerts for thresholds or deviations. Available connectors include PostgreSQL, MySQL, MariaDB, SQLite, and SQLAlchemy URIs; ClickHouse and Amazon Redshift are in beta, while SQL Server, Snowflake, BigQuery, Databricks, and dbt metadata are on the roadmap. Sema can run in a customer VPC or its own environment; self-hosting uses Kubernetes and Helm with customer-provided Postgres and object storage. The free Sandbox costs nothing and limits use to one connector, one user, 100 monthly chat queries, and five saved reports, without scheduled delivery or alerts. Pro costs $49 a month per user, with a three-seat minimum and a 14-day trial.