Ross ROSS = Recommend OSS · open-source software intelligence for agents

rilldata/rill

The fastest business intelligence tool for humans and agents. observed · 2026-08-28

github.com/rilldata/rill · homepage · Go · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

95/100

  • Activity 99
  • Release rhythm 87
  • Longevity 100
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 1
  • age_days: 1728
  • days_rel: 7
  • days_push: 7
  • n_releases_24m: 208

Full methodology

Adoption not part of the score

2844 stars · 196 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Rill is an open-source business intelligence tool that combines a local developer application and cloud platform for building interactive dashboards from OLAP engines like DuckDB and ClickHouse. It uses a BI-as-code approach (YAML + SQL) with a semantic layer, natural-language agentic analytics, and an MCP server so AI coding agents can author and query projects.

Use cases

  • build interactive BI dashboards from CSV, Parquet, or data warehouses
  • explore large datasets with sub-second SQL queries
  • let business users query metrics in natural language
  • scaffold and manage BI projects with AI coding agents like Claude Code or Cursor
  • define a semantic layer of dimensions and measures as code
  • embed analytics dashboards into your own application
  • connect AI agents to metrics via an MCP server

When to choose

  • you want fast, code-driven BI on DuckDB or ClickHouse with dashboards as YAML and SQL
  • your team wants AI agents to build and explore analytics end-to-end
  • you need embedded, brandable dashboards with API access and alerts
  • you want a local developer tool plus a managed cloud deployment path

When to avoid

  • you need a traditional drag-and-drop BI suite with no code
  • your data lives only in transactional (OLTP) databases without an OLAP engine
  • you require heavy custom pixel-perfect reporting rather than metric dashboards
  • you want a fully offline tool with no cloud component for sharing

Facets

application · maturity active

data-visualization analytics mcp chatbot etl search-engine data-visualization analytics large-language-models windows cli self-hosted go business-intelligence bi-as-code duckdb clickhouse semantic-layer dashboards sql parquet agentic-analytics embedded-analytics ai-agents data-engineering macos linux web-server

4 sources

Member repositories

RepositoryRoleHealth v2
rilldata/rillmain95

For agents

markdown · JSON · MCP: product_card(name="rilldata/rill")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem