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

lightdash/lightdash

Agentic BI. Analytics at the speed of code ⚡️ observed · 2026-08-28

github.com/lightdash/lightdash · homepage · TypeScript · NOASSERTION (other) observed · 2026-08-28

Health v2 · maintenance only

95/100

  • Activity 99
  • Release rhythm 87
  • Longevity 100

Flags: no_license

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: 0
  • age_days: 1993
  • days_rel: 7
  • days_push: 7
  • n_releases_24m: 4836

Full methodology

Adoption not part of the score

6084 stars · 770 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Lightdash is an open-source, agentic business intelligence platform that lets data teams define governed metrics, dashboards, AI agents, and data apps from a dbt- or YAML-based context layer. It supports BI-as-code workflows via Git, CI, CLI, and MCP, plus embedded analytics and conversational analytics with permission-aware AI agents.

Use cases

  • build dashboards and charts as code from a dbt project
  • let business users ask questions in plain English about governed data
  • embed analytics dashboards in a customer-facing product
  • review and validate analytics changes in pull requests and CI
  • self-host a BI tool with no per-seat pricing
  • build custom data apps and reports from a prompt
  • connect AI agents to a governed semantic layer via MCP

When to choose

  • your team uses dbt and wants metrics defined once in a semantic layer
  • you want BI versioned in Git with CI validation and code review
  • you need self-hosted or open-source BI without per-seat licensing
  • you want AI agents answering data questions with permissions and inspectable queries
  • you need embedded analytics with row-level security in your own product

When to avoid

  • you need a lightweight charting library to embed directly in frontend code
  • your data does not live in a SQL warehouse supported by dbt
  • you want a simple spreadsheet-style BI tool without a semantic layer
  • you cannot operate a self-hosted service and do not want a paid cloud plan

Facets

application · maturity active

data-visualization analytics rag chatbot mcp api-framework self-hosted developer-tools data-visualization analytics large-language-models self-hosted self-hosted cloud business-intelligence bi-as-code dbt semantic-layer agentic-bi dashboards data-apps embedded-analytics conversational-analytics data-engineering web-server docker nodejs typescript

3 sources

Member repositories

RepositoryRoleHealth v2
lightdash/lightdashmain95

For agents

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

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