Databend

Active
GitHub Rust NOASSERTION

Description

A Data Agent Ready Warehouse unifying Analytics, Search, AI, and Python Sandbox in one system. Runs on your S3 with built-in vector search, full-text search, and Python execution for AI-powered data analysis.

Key Features

  • Enterprise data warehouse built in Rust — analytics, vector search, full-text search, and auto schema evolution unified in one engine
  • Agent-ready architecture with Sandbox UDF for running Python agent logic, SQL orchestration, and transactions
  • Git-like data branching for safe experimentation on production data snapshots
  • Elastic cloud-native compute on S3, Azure, and GCS with separated storage and compute
  • Python sandbox UDFs enabling LLM calls and tool use directly within SQL functions
  • Docker one-liner local setup and free cloud tier for instant onboarding

Use Cases

💡 AI agent data backends — agents query and analyze enterprise data via SQL and Python UDFs
💡 Real-time analytics and BI on large-scale structured and semi-structured data
💡 Search and RAG pipelines combining vector embeddings with full-text search
💡 Data versioning and safe experimentation using Git-like branching
💡 Replacing legacy data warehouses with a modern, agent-native engine

Tags

database vector-database rag rust data-processing

Categories

📚 RAG Tools 🏗️ Sandbox & Execution

Quick Start

pip install 'databend-driver[local]>=0.34.0'
python3 -c "from databend_driver import connect; c=connect('databend+local:///./local-state'); print(c.query_row(\"SELECT 'Hello, Databend!'\").values())"
Visit GitHub

Related Projects