AI-native BI for your team — and the agents they work with
Cube gives your team and AI agents governed, reliable access to trusted business data through Analytics Chat, workbooks, dashboards, MCP, APIs, and CLI.
and 50+AI-native BI, built around the semantic layer from day one
Most BI tools are dashboard-first or notebook-first, with AI bolted on later. Cube was built around the semantic layer from day one — which is what makes the AI useful, not just present.
- Grounded answers, not guessesAI queries your governed model directly — no schema-guessing, no hallucinated metrics, no fifteen versions of active user.
- Same answer everywhereAsked in chat, a workbook, a dashboard, over MCP, or through an API — every answer ties back to the same governed definitions.
- Governance that flows throughRow-level security and access controls hold from the model down to every result a person or agent receives.
Built on Cube Core — the open-source semantic layer
Cube Core is Apache-licensed and battle-tested across years of production use. The agentic platform stands on a foundation you can read, run, and trust — not a closed box.
One governed BI platform for humans and agents
Analytics Chat
Natural-language analytics, grounded by default — no SQL required.
Workbooks
AI-augmented analyst exploration on the governed model.
Dashboards
AI-augmented visual reporting anyone can read.
AI agents
Trusted business context for the agents your team already uses.
Governance and flexibility — both, not either
The eternal BI tradeoff is governance versus flexibility. Cube's SQL-first semantic layer keeps the data team's definitions intact while AI agents and analysts build ad hoc calculations at query time.
- Fast under loadPre-aggregations and caching keep queries fast on big tables at high concurrency.
- Governed by default, flexible at query timeA SQL-first semantic layer that's extensible at query time, so AI agents and analysts don't wait for every new question to be modeled.
- One definition of every metricGovernance flows from the model into every human and agent workflow — no fifteen versions of active user.
Trusted business context for the agents your team already uses
Bring Cube to Claude, Codex, ChatGPT, Slack, and custom agent workflows. MCP, APIs, and CLI provide governed access without a separate data-access or permissions layer.
- MCP serverGive Claude, Codex, ChatGPT, and other MCP-compatible agents governed access to Cube.
- APIs and CLIConnect custom agents, automations, and development workflows to the same trusted business context.
- Slack agentBring natural-language analytics into your team's channels, governed by the same permissions and definitions.
Teams building with Cube
“The future of reporting isn't a chart, it's an insight. Large language models are becoming a commodity — the LLM is the engine, but the semantic layer is the map. A well-modeled ontology is the difference between 'I don't understand that question' and a correct, contextualized answer with a chart and a clear explanation. Cube gives us the foundation to make that real for every customer.”
Read the story“Cube becomes our single source of truth for metric definitions and powers everything from customer-facing dashboards to AI-driven quarterly business reviews. CSMs gain back dozens of hours each quarter, enabled by Cube’s semantic layer and agentic analytics.”
“We integrated Cube Cloud smoothly with ClickHouse, leveraging both for fast query execution while maintaining the abstraction needed for different teams to access data without diving into database-specific complexities.”
“Without Cube, our data analysts might have to write 20 different queries for a single core business metric. With Cube, that metric is defined once in the data model, and every downstream tool uses that definition along with the associated calculation logic.”
Bring governed BI to your team and AI agents
Give people and agents access to the same trusted definitions, permissions, and business context.