Science & Data

nao

Chat with your warehouse, self-hosted

Open ✓

What it is

An open framework for building and deploying analytics agents. You build a context layer over your data with the nao-core CLI, then deploy a chat interface so non-technical teammates can ask natural-language questions the agent answers against the warehouse. Warehouse-agnostic; bring your own LLM.

Why it's interesting

A genuinely open, self-hostable alternative to closed chat-with-your-data SaaS. The context-first design — curate the semantics before letting the agent query — is aimed squarely at the accuracy problems that plague simpler text-to-SQL tools.

Use cases

  • Natural-language analytics for business teams
  • Self-serve data Q&A
  • Deploying an internal data agent

Who it's for

Data engineers and analysts, analytics-engineering teams

Setup

Moderate. Python (nao-core) and Node.js; optional LLM API keys and a warehouse connection (BigQuery, Postgres, Snowflake, Databricks)

Limitations & cautions

Early-stage (v0.1.x) with a small community; answer quality is bounded by the curated context and the LLM you choose.

Editorial takeaway

The interesting bet here is architectural: fix the semantics first, and the agent stops hallucinating your revenue. Early, but pointed the right way.

Related & alternatives