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 is a framework for building and deploying analytics agents that allow business users to query their data using natural language. It bridges the gap between complex data warehouses and non-technical users by providing a chat interface for instant insights and visualizations.

How it works

Users create an agent's context—including data, metadata, documentation, and rules—using the nao-core CLI. This context is then synchronized and deployed via a chat UI. The framework is data-stack agnostic, meaning it works with various data warehouses and LLMs, and can be self-hosted for security.

Who it’s for

  • Data teams who want to provide reliable, self-service analytics to their organization while maintaining control over the agent's context and performance.
  • Business users who need quick answers to data questions in plain English without needing to know SQL or technical data structures.

Highlights

  • Open Context Builder: Create a file-system like context containing data, metadata, docs, and tools.
  • Native Data Visualization: Generate and customize charts and visualizations directly within the chat interface.
  • Agent Reliability Visibility: Includes an evaluation framework to unit test agent performance using expected SQL results before deployment.
  • Self-hosted & Secure: Supports self-hosting and the use of private LLM keys to ensure data privacy.
  • Transparent Reasoning: Users can see the agent's reasoning process and the sources used to generate an answer.

Related

  • 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
    Zafer-Liu/Data-Analysis-Agent

    Data‑Analysis‑Agent is a Flask‑based AI agent that turns natural‑language questions into SQL queries, runs them on uploaded files or connected databases, auto‑generates Plotly visualisations, and returns business insights. It works with any OpenAI‑compatible LLM, supports many chart types, and offers Windows installers, cross‑platform zip, or script‑based installation.

  • 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 a governed environment for building, evaluating, and deploying data agents.

  • Project
    Datus-ai/Datus-agent

    Datus is an open‑source Python agent that uses LLMs to automate data‑engineering tasks—semantic modeling, SQL generation, ETL pipeline creation, and report/dashboard building—while storing each interaction in a context engine that improves accuracy over time. It offers a CLI, web chat, and API, integrates with many databases, LLM providers, schedulers and BI tools, and is extensible via a plug‑in system.