# vanna-ai/vanna

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.

Repository: https://github.com/vanna-ai/vanna
Canonical: https://ross.abutalabs.com/products/vanna
Homepage: https://vanna.ai/docs/
Language: Python
License: MIT
License Family: permissive
Topics: agent, ai, data-visualization, database, llm, sql, text-to-sql, rag
Archived: true
Last push: 2026-02-02T14:14:20+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 65, release rhythm 68, longevity 86
- inputs: {"age_days": 1208, "days_push": 212, "days_rel": 212, "gap_med": 23.5, "n_releases_24m": 11}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 23818, forks 2486 (observed 2026-08-28T04:11:35.390175+00:00)

## What it is
Vanna is an open-source Python framework for building user-aware AI agents that translate natural-language questions into SQL queries, charts, and summaries against your database. It combines LLM tool use with agent memory that learns from successful question-SQL pairs, and ships with a streaming web chat component and FastAPI/Flask server integrations.

## Use cases
- chat with my sql database in natural language
- generate sql queries from plain english questions
- build a text-to-sql ai agent for postgres or snowflake
- let non-technical users query a database with llm
- auto-generate charts and tables from natural language questions
- add row-level security to an ai data assistant
- embed a chat interface for database analytics in a web app

## When to choose
- you want users without SQL skills to explore relational databases via natural language
- you need a production-ready text-to-SQL agent with auth, audit logs, and rate limiting
- you want an agent that improves over time by remembering successful question-SQL pairs
- you need flexibility across many LLM providers and SQL databases

## When to avoid
- you need general-purpose LLM agents unrelated to SQL or databases
- you require guaranteed-correct SQL without human review, since LLM-generated queries can be wrong
- you want a no-code hosted product only - Vanna is a developer framework requiring Python integration

## Facets
- artifact type: library
- maturity: active
- function: agent-framework, rag, llm-inference, data-visualization, database, chatbot, api-framework
- domain: large-language-models, databases, data-science, analytics, developer-tools
- platform: python, self-hosted, cross-platform
- tags: text-to-sql, nl2sql, sql-agent, plotly, fastapi, streaming, row-level-security, agent-memory, vector-store, ai-agents, retrieval-augmented-generation, web-server

## Member repositories
- vanna-ai/vanna (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:35.390175+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:56:20.081738+00:00, confidence not recorded.
  - readme: https://github.com/vanna-ai/vanna (fetched 2026-08-28T04:11:35.390175+00:00, sha a33e25732076)
  - homepage: https://vanna.ai/docs/ (fetched 2026-08-29T07:53:57.859784+00:00, sha 73665e813b52)
  - site_page: https://vanna.ai/docs/quick-start (fetched 2026-08-29T07:53:57.871217+00:00, sha 91b303fe5a0e)
  - site_page: https://vanna.ai/docs/configure (fetched 2026-08-29T07:53:57.872977+00:00, sha 96ccc2af678a)
  - site_page: https://vanna.ai/docs/migration (fetched 2026-08-29T07:53:57.874919+00:00, sha 441bfd65b5b7)
  - registry_pypi: https://pypi.org/pypi/vanna/json (fetched 2026-08-29T07:53:57.876923+00:00, sha 09534a9d9472)
  - site_page: https://vanna.ai/ (fetched 2026-08-29T07:53:57.869024+00:00, sha 791ac96de8ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.