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

Canner/WrenAI

GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data sources, such as BigQuery, Snowflake, PostgreSQL, ClickHouse, Amazon Redshift, Databricks and more. observed · 2026-08-28

github.com/Canner/WrenAI · homepage · Python · NOASSERTION (other) observed · 2026-08-28

Health v2 · maintenance only

87/100

  • Activity 99
  • Release rhythm 86
  • Longevity 64

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: 4.0
  • age_days: 903
  • days_rel: 15
  • days_push: 7
  • n_releases_24m: 75

Full methodology

Adoption not part of the score

17401 stars · 1970 forks observed · 2026-08-28

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

WrenAI is an open-source generative BI (GenBI) engine that turns natural-language questions into governed SQL, charts, and dashboards across 20+ data sources like BigQuery, Snowflake, PostgreSQL, and ClickHouse. It provides an open AI context layer with a semantic layer (MDL) so AI agents and humans get trustworthy, business-grounded answers instead of schema guesses.

Use cases

  • ask business questions in plain English and get SQL answers
  • generate dashboards and charts from natural language
  • text-to-SQL over Snowflake, BigQuery, Postgres, ClickHouse, Databricks
  • give AI agents a governed semantic layer over warehouse data
  • expose business data to agents via MCP
  • define metrics and business logic once in a version-controlled MDL
  • self-host a governed AI analytics platform

When to choose

  • you want open-source, self-hostable text-to-SQL with governance
  • your team needs natural-language BI on existing warehouses without migrating data
  • you're building AI agents that must query business data reliably
  • you need a semantic layer with approved metric definitions in git

When to avoid

  • you need a traditional hand-built BI tool without LLM involvement
  • you want a fully closed-source managed product with vendor SLAs only
  • your use case is simple SQL editing rather than natural-language analytics

Facets

application · maturity active

rag llm-inference agent-framework mcp data-visualization search-engine api-framework cli large-language-models databases analytics data-visualization self-hosted python self-hosted cloud cli text-to-sql genbi semantic-layer mdl context-layer business-intelligence nl2sql data-connectors open-core ai-agents retrieval-augmented-generation docker web-server

7 sources

Member repositories

RepositoryRoleHealth v2
Canner/WrenAImain87

For agents

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

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