Skip to content
repository radar
Infra, Data & Ops

💡Vanna

OFF THE RADAR ARCHIVED

vanna-ai/vanna · homepage ↗

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

⭐ Very popular: 24k stars, gaining about 17 a week

View on GitHub ↗

repo profile

vintage 2023 3 years old
delivery library
language Python
license MIT

momentum

total stars 24k
stars added last week +17
HN peak 547 pts 2y 7mo ago
weekly downloads 46k /wk · PyPI
commits / week 0 steady
issues closed 36% ~3d to close, median
contributors 88
release cadence quarterly
last activity 6mo ago

durability

backing VC-backed Vanna AI
openness permissive

since we covered it

monthly average + 326/mo (+2%/mo) · + 4k total since PR#13

why it's a big deal

  • Lets non-technical users chat with SQL databases through Slack, Streamlit, Flask, Chainlit, and more.
  • Ships a strong ecosystem of adapters for OpenAI, ChromaDB, Pinecone, and other vector stores.
  • Agentic RAG approach produces accurate text-to-SQL that improves as it learns your schema and queries.

under the hood

  • A Python RAG pipeline: index documentation, then prompt an LLM to generate SQL.
  • Modular, provider-agnostic architecture built around a VannaBase core.
  • Deploys across Slack, web apps, and Jupyter notebooks.

our take from PR#13, 2025-07-23

star history

PR#13 · 20k24k now May 2023Aug 2026
  1. PR#13 20k 2025-07-23
  2. now 24k + 4k since first covered

curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.

understory

Better known than its recent output, coasting a little on attention.

-55 understory score output 0 · clout 55
Aug 2025 Jul 2026
  • output, commits & releases
  • clout, star velocity

output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →

covered in

  • PR#13 2025-07-23 on the radar

    Natural-Language Interface for SQL Databases

similar projects

compare these →
  • 📊 Wren AI

    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.

    17k ACTIVE
  • 🗜️ headroom

    2.8× the stars

    Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

    66k ACTIVE
  • 🧠 Memori

    Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.

    16k ACTIVE

comments

Sign in with GitHub to add your blip on Vanna.

loading comments…