Large-scale analytics, vector search, full-text search — with flexible agent orchestration and secure Python UDF sandboxes. Built for enterprise AI workloads.

☁️ Try Cloud • 🚀 Quick Start • 📖 Documentation • 💬 Slack

Databend is an open-source enterprise data warehouse built in Rust.

Core capabilities: Analytics, vector search, full-text search, auto schema evolution — unified in one engine.

Agent-ready: Sandbox UDFs for agent logic, SQL for orchestration, transactions for reliability, branching for safe experimentation on production data.

Start for free on Databend Cloud — Production-ready in 60 seconds.

Ideal for development and testing. Requires Python 3.12 or 3.13 and databend-driver 0.34.0 or later:

pip install "databend-driver[local]>=0.34.0"

from databend_driver import connect

conn = connect("databend+local:///./local-state")
print(conn.query_row("SELECT 'Hello, Databend!'").values())

Run the full warehouse locally:

docker run -p 8000:8000 datafuselabs/databend

Databend's Sandbox UDF enables flexible agent orchestration with a three-layer architecture:

• Control Plane: Resource scheduling, permission validation, sandbox lifecycle management
• Execution Plane (Databend): SQL orchestration, issues requests via Arrow Flight
• Compute Plane (Sandbox Workers): Isolated sandboxes running your agent logic

-- Define your agent logic
CREATE FUNCTION my_agent(input STRING) RETURNS STRING
LANGUAGE python HANDLER = 'run'
AS $$
def run(input):
    # Your agent logic: LLM calls, tool use, reasoning...
    return response
$$;

-- Orchestrate agents with SQL
SELECT my_agent(question) FROM tasks;

• AI Agents: Sandbox UDF + SQL orchestration + branching for safe operations
• Analytics & BI: Large-scale SQL analytics — Learn more
• Search & RAG: Vector + full-text search — Learn more

• 📖 Documentation
• 💬 Join Slack
• 🐛 Issue Tracker
• 🗺️ Roadmap

Contributors are immortalized in the system.contributors table 🏆

Apache 2.0 + Elastic 2.0 | Licensing FAQ