rill
The fastest business intelligence tool for humans and agents.
What is rill?
The fastest business intelligence tool for humans and agents.
Overview of rill
What it is
Rill is an open-source business intelligence tool designed for both human users and AI agents. It is powered by OLAP engines such as ClickHouse and DuckDB, and emphasizes a code-first approach where dashboards, metrics, and data models are defined in YAML and SQL. The project is licensed under Apache-2.0 and is categorized under Analytics.
Key features
- Build with agents: BI-as-code (YAML + SQL) enables coding agents like Claude Code and Cursor to author projects, dashboards, and security policies end-to-end - Semantic layer: A single source of truth for dimensions, measures, and time grains defined in YAML, generating SQL at query time against the OLAP engine - Explore with agents: Conversational BI allows business users to query metrics in natural language; the MCP server connects AI agents directly to the semantic layer - Real-time performance: Sub-second queries at any scale; ClickHouse for billions of rows, DuckDB for smaller datasets and fast iteration - Embeddable: Dashboards, APIs, and agent interfaces that can be shipped in a product
Use cases
Rill can be used for building and deploying interactive dashboards, performing ad-hoc data exploration, setting up alerts and reports, and embedding analytics into products. It supports conversational BI for natural language queries and integrates with AI agents via an MCP server. Example use cases include programmatic ads analysis, cost monitoring, and GitHub analytics.
Getting started
bash curl https://rill.sh | sh # install rill start my-project # create a project and open the UI To scaffold a project interactively with agent context, run rill init.
License and pricing
The project is licensed under Apache-2.0 and is open source. Pricing for Rill Cloud is not stated in the provided README.
Based on the project's public README and repository metadata.