What is Nao used for?

Nao is an open-source framework for building and deploying a chat-based analytics agent that answers questions about your data warehouse in plain English. It is a good fit for letting business users query a warehouse in plain English, testing analytics agent accuracy before rollout and collecting feedback on AI-generated answers.

Yes. Nao is open source under a custom licence. Its source code is on GitHub at getnao/nao and is written mainly in TypeScript.

Yes. Nao is open source, so the software itself is free to use under the terms of its own licence.

Yes. Nao can be self-hosted on your own server or infrastructure.

What is Nao an alternative to?

Nao is an open-source alternative to ThoughtSpot, Julius AI, Tellius and Akkio. Other open-source alternatives to ThoughtSpot include DB-GPT, Lightdash and Frappe Insights.

Is Nao actively maintained?

Yes. The most recent commit to Nao was on 2 October 2026, and the latest release is v0.3.19, published on 30 September 2026. The project has 1.7k stars on GitHub.

Nao: open-source alternative to ThoughtSpot, Julius AI

About Nao

nao is an open-source framework for building an analytics agent and deploying it as a chat interface. Data teams assemble the agent's context with the nao-core command-line tool, then give business users a UI where they can ask questions in natural language and receive analysis, charts and the reasoning behind each answer.

On the data team side, the context builder works like a file system and can include data, metadata, documentation, tools and MCP servers. The framework is described as stack-agnostic, with topics pointing to BigQuery, Snowflake, Databricks and PostgreSQL. Teams can unit test the agent's performance before release, version the context, track usage and collect feedback from users who mark answers right or wrong.

nao is written in TypeScript and is designed to be self-hosted with your own LLM keys, which keeps data under your control. A Slack connection is available as an option during setup. It suits data and analytics engineering teams who want a governed text-to-SQL assistant for the rest of the company rather than ad hoc prompts.

Key features

Chat interface for natural-language analytics
Context builder for data, docs, and MCPs
Agent unit tests and performance tracking
Built-in data visualization in chat
Optional Slack connection
Bring your own LLM keys

Good fit for

→Letting business users query a warehouse in plain English
→Testing analytics agent accuracy before rollout
→Collecting feedback on AI-generated answers

Built with: TypeScript; PostgreSQL
Tags: analytics; text-to-sql; ai-agent; chat-with-data; self-hosted; bigquery; snowflake; slack-bot; typescript

Nao: questions and answers

What is Nao used for?: Nao is an open-source framework for building and deploying a chat-based analytics agent that answers questions about your data warehouse in plain English. It is a good fit for letting business users query a warehouse in plain English, testing analytics agent accuracy before rollout and collecting feedback on AI-generated answers.
Is Nao open source?: Yes. Nao is open source under a custom licence. Its source code is on GitHub at getnao/nao and is written mainly in TypeScript.
Is Nao free?: Yes. Nao is open source, so the software itself is free to use under the terms of its own licence.
Can I self-host Nao?: Yes. Nao can be self-hosted on your own server or infrastructure.
What is Nao an alternative to?: Nao is an open-source alternative to ThoughtSpot, Julius AI, Tellius and Akkio. Other open-source alternatives to ThoughtSpot include DB-GPT, Lightdash and Frappe Insights.
Is Nao actively maintained?: Yes. The most recent commit to Nao was on 2 October 2026, and the latest release is v0.3.19, published on 30 September 2026. The project has 1.7k stars on GitHub.