What is Vanna 2.0?
Vanna 2.0 is a user-aware AI agent framework that connects LLMs to your database.
The Core Concept
At its heart, Vanna is simple:
- Connect tools to an LLM - Give your AI agent the ability to run SQL queries, generate charts, or any custom functionality
- Remember how to use them - Tool Memory learns from successful interactions, getting better over time
- Enforce permissions - Every user has specific access controls that flow through the entire system
How It Gets Better Over Time
Every successful interaction is saved to Tool Memory. When a user asks a similar question:
- The agent searches past SQL queries and tool usage patterns
- It adapts successful examples to the current context
- Your agent learns your database schema, business logic, and query patterns without manual training
Novel Question (Left Path) - Deeper investigation, saves to memory
Similar Question (Right Path) - Fast adaptation from memory
Loading diagram...
🚀 Getting Started
Quickstart with Sample Data
Use the sample Chinook SQLite database
Quickstart with Your Own Data
Connect to your database in Python
Migrate from 0.x
Moving from Vanna 0.x to v2
💬 Community and Support
- GitHub Repository
- Issues – Report bugs or request features
- Discussions – Ask questions and share examples