rilldataData & analytics
rill
A code-first business intelligence platform that uses SQL and YAML to define metrics and provides data access interfaces for AI agents.
- Backend
- Full stack
- Data
- Data analysis
- Automation
- Productivity
- CLI
- Web
- API/SDK
- macOS
- Linux
- Windows
- Self-hostable
- Runs locally
- Docker supported

- Popularity
- 2.8k Stars
- GitHub stars
- Recent activity
- 8/25/2026
- Updated in the last 30 days
- License
- APACHE-2.0
- Permissive
Why it matters
We look beyond stars: what problem it solves, whether it creates real utility, and what makes its approach worth noticing.
Problem
Addresses the friction in traditional BI tools regarding configuration complexity, lack of version control, and poor integration with AI agents.
Practical value
Utilizes YAML and SQL for semantic layer definition, supports local development previews and cloud deployment, and provides an MCP server for direct AI access to metrics.
Innovation / differentiation
Implements a BI-as-code approach with native AI Agent support, exposing data analysis capabilities to LLMs via the MCP protocol.
Leverage potential
Leverages high-performance OLAP engines like DuckDB and ClickHouse to handle analytical needs ranging from local small datasets to large-scale data.
Why now
Arrives at a time when AI Agent development paradigms are emerging, offering a way to integrate data analysis workflows with automated coding tools.
Community activity
In the last 90 days there were 5 new issues and 321 pull requests; the bounded issue/PR samples include 5 issue authors and 11 PR contributors, with at least 18 releases.
Maintainer responsiveness
The 5-issue window sample had a 20% close rate, and the 98-pull-request sample had a 92% merge rate. Maintainer-comment observations covered only 80% of that issue sample, so response rate and first-response speed are not reported.
Key highlights
- YAML-based semantic layer definition
- AI agent-native dashboard authoring for tools like Claude Code
- Built-in support for DuckDB and ClickHouse
Quick start
How it is installed, how hard it is, and where to start.
Where it runs
Runs locally
Difficulty
Medium — some setup needed
- 01Install the Rill CLI using the provided curl command.
- 02Run
rill initto initialize your project and configure the OLAP engine. - 03Define data models and metrics by creating YAML and SQL files in the
modelsandmetricsdirectories. - 04Run
rill startto launch the dashboard locally for preview. - 05Use
rill deployto push your project to Rill Cloud.
Best for
- Teams that want data on their own servers
- Developers who want to try it on their machine
- People who prefer Docker deploys
More about it
Rill is a business intelligence platform designed for developers and AI agents. By defining data models, metrics, and dashboards as code (YAML and SQL), it enables version control and automation for BI workflows. Users can model and explore data locally with Rill Developer and deploy interactive, embeddable dashboards via Rill Cloud.
The platform exposes metrics to AI agents via an MCP (Model Context Protocol) server, allowing AI to understand business semantics and perform natural language queries. Rill supports various data sources and leverages DuckDB or ClickHouse for real-time query performance.
Sources
Each field shows its status and source — expand to review.
12 · Expand
Sources
Each field shows its status and source — expand to review.
capability tags
Verifieddata_analysis, automation, productivity
Source: admin_cms · cms editor · 8/18/2026
Latest release
Verifiedv0.89.1
Source: GitHub API · latest_release=v0.89.1 · 8/25/2026
License
VerifiedApache-2.0
Source: GitHub API · license.spdx_id=Apache-2.0 · 8/25/2026
needs api key
VerifiedNo
Source: admin_cms · cms editor · 8/14/2026
One-liner
Verified{"en":"A code-first business intelligence platform that uses SQL and YAML to define metrics and provides data access interfaces for AI agents.","zh":"基于代码的商业智能平台,支持通过 SQL 和 YAML 定义指标,并为 AI 代理提供数据访问接口。"}
Source: heuristic_batch_publish · batch-publish-tools heuristic write · 8/24/2026
Platforms
Verifiedmacos, linux, windows
Source: admin_cms · cms editor · 8/14/2026
Category hint
Inferred from materialsai-apps
Source: Project README · hint=ai-apps · 8/14/2026
product forms
Verifiedcli, web, api_sdk
Source: admin_cms · cms editor · 8/18/2026
role tags
Verifiedbackend, fullstack, data
Source: admin_cms · cms editor · 8/18/2026
supports docker
VerifiedYes
Source: Repository file · dockerfile=true; compose=true · 8/25/2026
supports local
VerifiedYes
Source: admin_cms · cms editor · 8/14/2026
supports self host
VerifiedYes
Source: admin_cms · cms editor · 8/14/2026
Related projects
Other verified projects matched by category, capabilities, and intended roles.
clearml
A machine-learning development and MLOps platform for experiment tracking, remote orchestration, data versioning, and model workflows with hosted or self-hosted servers.
liam
A tool that generates interactive ER diagrams from existing database schemas through public-repository links or a CLI workflow for private repositories.
Rath
A visual exploratory-data-analysis tool that recommends charts and insights while supporting manual exploration, data wrangling, and experimental causal analysis.
Apache DevLake
An engineering data platform that unifies sources such as GitHub, GitLab, Jira, Jenkins, and SonarQube for DORA and delivery analytics in Grafana.
ragflow
An open-source RAG engine fusing deep document understanding and agent capabilities to build grounded context layers for LLMs.
mcp-dashboards
An MCP server that renders interactive charts, dashboards, and KPI widgets directly inside AI chat clients.