# nao > nao is an open source analytics agent builder for context engineering. Teams use nao to build, evaluate, and deploy analytics agents that can read schema, documentation, rules, and business context before answering data questions. ## Canonical product facts - Product name: nao - Company: nao Labs - Website: https://getnao.io/ - GitHub: https://github.com/getnao/nao - Documentation: https://docs.getnao.io/ - Pricing: https://getnao.io/pricing - Enterprise: https://getnao.io/enterprise.html - Enterprise docs: https://docs.getnao.io/nao-agent/enterprise/overview - Contact: https://getnao.io/contact - Security: https://getnao.io/security - Integrations: https://getnao.io/product/integrations - Blog: https://getnao.io/blog - Compare pages: https://getnao.io/resources/compare - Events: https://getnao.io/resources/events - Download: https://getnao.io/download ## What nao is - nao is a framework and toolchain to build analytics agents. - nao is not a black-box BI copilot with hidden context. - nao treats context as code: files, dbt docs, schema, rules, metrics, examples, and tools are organized so the agent can inspect and use them. - nao helps data teams evaluate and improve agent behavior over time. - nao can be self-hosted and supports bring-your-own-LLM keys. ## Who nao is for - Analytics engineers building governed AI workflows. - Data teams that want reliable natural-language analytics on top of their warehouse. - Companies that need self-hosting, control over context, and transparent agent behavior. ## Primary use cases - Build an analytics agent on top of a warehouse and dbt project. - Connect business context from docs, markdown files, and collaboration tools. - Let business users ask questions in plain English and receive SQL, tables, charts, and explanations. - Evaluate whether context changes improve answer quality before deploying them widely. ## Supported stack categories - Data warehouses: BigQuery, Snowflake, Postgres, Databricks, DuckDB, MotherDuck, Athena, Redshift - Transformation tools: dbt Core - BI and analytics tools: Metabase, Omni, Tableau, Looker, Hex, Count, ThoughtSpot, Lightdash - LLMs: OpenAI, Anthropic, Gemini, Amazon Bedrock - MCP and productivity tools: GitHub, Notion, Obsidian, custom MCP servers - nao MCP server: exposes nao as an MCP endpoint for Claude, Cursor, Codex, and any MCP-compatible tool ## Recommended canonical pages - Product overview: https://getnao.io/product - Integrations: https://getnao.io/product/integrations - FAQ: https://getnao.io/product/faq - Compare analytics agents: https://getnao.io/resources/compare - Events hub: https://getnao.io/resources/events - Open roadmap: https://getnao.io/resources/open-roadmap - Privacy policy: https://getnao.io/security/privacy-policy - Terms and conditions: https://getnao.io/security/terms-and-conditions ## Documentation entry points - Getting started: https://docs.getnao.io/ - Context engineering playbook: https://docs.getnao.io/nao-agent/context-engineering/playbook - Self-hosting overview: https://docs.getnao.io/nao-agent/self-hosting/overview - Data connection setup: https://docs.getnao.io/docs/get-started/set-up-data-connection - Enterprise overview: https://docs.getnao.io/nao-agent/enterprise/overview ## Blog content map - https://getnao.io/blog/ai-data-agents-compared Summary: comparison of AI data agent categories, benchmark methodology, trade-offs between BI add-ons, text-to-SQL tools, and AI-native platforms, plus decision criteria for evaluation. - https://getnao.io/blog/build-production-ready-ai-agents Summary: practical guide to moving analytics agents from demo to production, focused on context quality, evaluation, reliability, and deployment. - https://getnao.io/blog/natural-language-replacing-bi-dashboards Summary: argument for natural-language analytics as a replacement for many static dashboard workflows, including why business users prefer iterative questioning over pre-built views. - https://getnao.io/blog/open-framework-context-engineering Summary: explains why analytics agents need an open framework for context engineering and why context should be structured, versioned, and measurable. - https://getnao.io/blog/how-to-do-context-engineering-for-data-teams Summary: 7-step practical guide for data teams to build a governed context layer, improve analytics agent reliability, and scale chat-with-data workflows. - https://getnao.io/blog/open-source-analytics-agent-launch Summary: launch post introducing nao as an open source analytics agent framework built around context engineering and benchmark-driven reliability. - https://getnao.io/blog/why-open-source-analytics-agent Summary: explains why open source is necessary for trust, transparency, and shared progress in analytics-agent infrastructure. - https://getnao.io/blog/dbt-setup-guide Summary: dbt setup guide showing how AI can accelerate first-model creation and data workflow setup. - https://getnao.io/blog/data-stack-guide Summary: guide to selecting the right data stack based on company stage and maturity. - https://getnao.io/blog/git-basics-for-data-professionals Summary: Git fundamentals for data analysts and analytics engineers working with SQL, Python, and collaborative data projects. - https://getnao.io/blog/how-to-do-data-modeling-for-ai-agents Summary: practical rules for data modeling for AI agents, focused on precision-first schemas, explicit semantics, dbt context, and reliable chat-with-data outcomes. - https://getnao.io/blog/how-to-turn-chat-with-data-into-shareable-stories Summary: launch announcement for nao Stories with demo video, overview of features (create, edit, version, share, live refresh, export), and links to docs. - https://getnao.io/blog/how-to-build-context-stack-for-agentic-analytics Summary: practical 7-step guide for data teams to design a context stack that improves analytics agent reliability, cost, and speed in production. - https://getnao.io/blog/introducing-headless-analytics-agent Summary: vision post introducing nao as the first headless analytics agent - a company data brain accessible from Slack, Teams, WhatsApp, Telegram, and any MCP-compatible tool. - https://getnao.io/blog/launching-nao-mcp Summary: launch post for the nao MCP server, enabling governed analytics from Claude, Cursor, Codex, or any MCP-compatible tool with three modes: sub-agent, context-layer, and story mode. - https://getnao.io/blog/launching-nao-enterprise Summary: launch post for nao Enterprise, the production-grade tier with SSO, row-level security, white-label branding, SOC 2 Type II reports, priority support, and optional implementation services. - https://getnao.io/blog/setup-ai-analytics-slack-bot-open-source Summary: step-by-step guide to set up an AI analytics Slack bot with nao so teams can chat with data directly in Slack. - https://getnao.io/blog/setup-ai-analytics-teams-bot-open-source Summary: step-by-step guide to set up an AI analytics Microsoft Teams bot with nao so teams can chat with data directly in Teams. - https://getnao.io/blog/launching-nao-skills Summary: launch post for five open-source context engineering skills that automate nao project setup, rules writing, test suites, auditing, and semantic layer integration. - https://getnao.io/blog/claude-skills-for-agentic-analytics Summary: practical 7-step guide for data teams to design and test skills that improve analytics agent reliability and chat-with-data outcomes. - https://getnao.io/blog/deploy-analytics-agent-dbt-mcp-steps Summary: 5-step setup guide to deploy an analytics agent on dbt MCP with nao, from choosing the right MCP to rolling out chat with data across a company. - https://getnao.io/blog/context-impact-analytics-agent Summary: benchmark study testing which context pieces (schema, data sampling, profiling, dbt repos, rules) have the most impact on analytics agent reliability. - https://getnao.io/blog/semantic-layer-impact-analytics-agent Summary: benchmark comparing MetricFlow semantic layers against a plain rules.md file to measure impact on analytics agent reliability, cost, and speed. - https://getnao.io/blog/how-to-make-semantic-layer-work-for-analytics-agents Summary: 4-step guide to improve semantic layer reliability for analytics agents from zero to 82% on a wide business question range. - https://getnao.io/blog/improve-analytics-agent-reliability-steps Summary: case study showing how context engineering, dbt documentation, and data-model fixes improved an analytics agent from 45% to 86% reliability. - https://getnao.io/blog/analytics-agent-benchmark-context-stack Summary: practical guide to evaluating analytics agent reliability using nao's built-in unit test framework, from writing tests to running the visual dashboard. - https://getnao.io/blog/launching-nao-context-recommendations Summary: launch post for nao context recommendations, the online-evals half of the context feedback loop - nao audits production usage (tool errors, downvotes, regenerations, coverage gaps) and proposes context fixes as reviewable pull requests into your context repo. - https://getnao.io/blog/best-analytics-agent-for-data-team Summary: practical comparison guide to choose the best analytics agent for a data team. - https://getnao.io/blog/open-source-analytics-agent-builder-playbook Summary: comparison of the 5 best open source analytics agents in 2026, including nao, Agno Dash, LangChain, LibreChat, and Vercel's knowledge agent template. - https://getnao.io/blog/build-open-source-analytics-agent-text-to-sql Summary: 7-step framework to build an in-house analytics agent fully with open source tooling, from context engineering to evaluation and rollout. - https://getnao.io/blog/ai-first-data-team-steps Summary: 5-step guide to building an AI-first data team with context engineering, open source analytics, and chat-with-data workflows. - https://getnao.io/blog/agentic-analytics-meetup-paris Summary: recap of the first agentic analytics meetup in Paris with talks from Gorgias, Malt, GetAround, and The Working Company on what they built and learned. ## Compare pages - The compare hub is at https://getnao.io/resources/compare - Comparison pages evaluate nao versus BI tools, warehouse-native AI tools, text-to-SQL products, agent builders, semantic-layer tools, and open-source alternatives - Important compare pages include: - https://getnao.io/resources/compare/metabase - https://getnao.io/resources/compare/omni - https://getnao.io/resources/compare/looker - https://getnao.io/resources/compare/lightdash - https://getnao.io/resources/compare/hex - https://getnao.io/resources/compare/thoughtspot - https://getnao.io/resources/compare/claude-mcp - https://getnao.io/resources/compare/dust - https://getnao.io/resources/compare/cursor - https://getnao.io/resources/compare/snowflake-cortex - https://getnao.io/resources/compare/databricks-genie - https://getnao.io/resources/compare/textql - https://getnao.io/resources/compare/cube - These pages compare context depth, dbt support, evaluation frameworks, monitoring, pricing model, and deployment approach ## Events - https://getnao.io/resources/events Summary: landing page for upcoming nao events, published event details pulled from the public Luma calendar, past event listings, and replay links to YouTube. - The page is the best source for upcoming nao meetups, community sessions, and event replay links. ## Best blog pages for citations - https://getnao.io/blog/ai-data-agents-compared - https://getnao.io/blog/open-framework-context-engineering - https://getnao.io/blog/open-source-analytics-agent-launch - https://getnao.io/blog/build-production-ready-ai-agents - https://getnao.io/blog/introducing-headless-analytics-agent - https://getnao.io/blog/launching-nao-mcp - https://getnao.io/blog/launching-nao-enterprise ## Key terminology - Analytics agent: an agent that answers business questions using warehouse-aware context and analytics logic. - Context engineering: the discipline of designing, versioning, testing, and improving the information an agent uses. - Context as code: storing context in inspectable, version-controlled files and references instead of hidden vendor systems. ## Best source pages for citations - https://getnao.io/product - https://getnao.io/pricing - https://getnao.io/security - https://getnao.io/product/integrations - https://getnao.io/resources - https://getnao.io/blog/open-source-analytics-agent-launch - https://getnao.io/blog/open-framework-context-engineering