getnao/nao

👾 nao is an open source analytics agent. (1) Create context with nao-core cli, (2) deploy nao chat interface for everyone

What it solves

nao provides a framework for data teams to build and deploy analytics agents that allow business users to query data using natural language instead of writing complex SQL queries manually.

How it works

Users create an agent's context—including data, metadata, documentation, and rules—using a CLI tool (nao-core). This context is synchronized with the agent, which then translates plain English questions into data insights. The system includes a chat interface for users to interact with the agent, visualize data, and provide feedback, while data teams can unit test the agent's performance using a dedicated evaluation framework.

Who it’s for

  • Data teams who want to build reliable, secure, and data-stack-agnostic analytics agents.
  • Business users who want to get instant analytics and visualizations from their data without needing technical expertise.

Highlights

  • Open Context Builder: Supports adding data, metadata, docs, and MCPs without limits.
  • Data Stack Agnostic: Compatible with any LLM, data warehouse, or data stack.
  • Agent Reliability Visibility: Includes tools to unit test performance, version context, and track usage/feedback.
  • Self-hosted & Secure: Allows self-hosting and the use of private LLM keys to ensure data security.
  • Native Visualization: Generates and allows customization of data visualizations directly within the chat UI.

Related

  • Project
    Datus-ai/Datus-agent

    An open-source data engineering agent that automates SQL authoring, semantic modeling, and pipeline generation by connecting warehouses, catalogs, and BI tools through a learning context engine.

  • Project
    holoviz/lumen

    An open-source agent-based framework for chatting with data and RAG, enabling users to generate data pipelines and visualizations via natural language.

  • Project
    cloudwego/eino

    An LLM application development framework for Golang that provides tools for building AI agents, multi-agent coordination, and graph-based workflows.

  • Project
    bagofwords1/bagofwords

    An open-source agentic analytics platform that connects LLMs to enterprise data and tools, providing governed context and self-improving loops for reliable data analysis.

  • Project
    lealone/Lealone

    A high-performance full-stack self-evolving agent that enables the creation of enterprise AI applications and full-stack apps via natural language and SQL-like service definitions.