getnao / nao

nao The #1 Open-Source Analytics Agent 🌐 Website · 📚 Documentation · 💬 Slack What is nao? nao is a framework to build and deploy analytics agent. Create the context of your analytics agent with nao-core cli: data, metadata, modeling, rules, etc. Deploy a UI for anyone to chat with your agent and run analytics on your data. Key Features For **data teams**: • 🧱 **Open Context Builder** — Create a file-system like context for your agent. Add anything you want in the context: data, metadata, docs, tools, MCPs. No limit. • 🏳️ **Data Stack Agnostic** — Works with any data warehouse, stack, type of context, LLM. • 🕵🏻‍♀️ **Agent Reliability Visibility** — Unit test your agent performance before deploying it to users. Version the context and track the performance of your agent over time. Get users feedbacks to improve the agent and track their usage. • 🔒 **Self-hosted & secure** — Self-host your analytics agent and use your own LLM keys to guarantee maximum security for your data. For **business users**: • 🤖 **Natural Language to Insights** — Ask questions in plain English, get analytics straight away • 📊 **Native Data Visualization** — Create and customize visualizations directly in the chat interface • 🧊 **Transparent Reasoning** — See the agent reasoning and sources clearly • 👍 **Easy Feedback** — Send feedback to the data team when a answer is right or wrong ⚡️ Quickstart your agent in 1 minute • **Step 1**: Install nao-core package • **Step 2**: Initialize a nao project It will ask you: • To name your project • If you want to connect a database _(optional)_ • If you want to add a repo in agent context _(optional)_ • To add an LLM key _(optional)_ • If you want to setup a Slack connection _(optional)_ 💡 You can skip any optional question and configure them later in your file. This will create: • A new folder with your project name • An architecture for your context files • A configuration file • A file • **Step 3**: Verify your setup cd to the project folder and run: • **Step 4**: Synchronize your context This will populate your context folder with your context files (data, metadata, repos, etc.) • **Step 5**: Launch the chat and ask questions This will start the nao chat UI. It will open the chat interface in your browser at . From there, you can start asking questions to your agent. Evaluation framework Unit test your agent performance before deploying it to users. First, create a folder with questions and expected SQL in yaml. Then, measure agent's performance on examples with nao test command: View results in tests panel: Commands 🐳 Docker Pull the image from DockerHub: Run nao chat with Docker using the example project bundled in the image: Run nao chat with Docker using your local nao project: Access the UI at http://localhost:5005 (or at any URL you configured). See the DockerHub page for more details. For end-to-end self-hosted deployment (for example on Cloud Run with PostgreSQL), see the Deployment Guide. 👩🏻‍💻 Development See CONTRIBUTING.md for development setup, commands, and guidelines. 📒 Stack Backend • Fastify: https://fastify.dev/docs/latest/ • Drizzle: https://orm.drizzle.team/docs/get-started • tRPC router: https://trpc.io/docs/server/routers Frontend • tRPC client: https://trpc.io/docs/client/tanstack-react-query/usage • Tanstack Query: https://tanstack.com/query/latest/docs/framework/react/overview • Shadcn: https://ui.shadcn.com/docs/components ⛹️‍♀️ Join the Community • Star the repo • Subscribe to releases (Watch → Custom → Releases) • Follow us on LinkedIn • Join our Slack • Contribute to the repo! 🫰🏻 Partners nao Labs is a proud Y Combinator company! 📄 License This project is licensed under the Apache 2.0 License - see the LICENSE file for details.