lightdash/lightdash

Agentic BI. Analytics at the speed of code ⚡️

What it solves

Lightdash provides a governed approach to business intelligence (BI) that treats analytics like software. It solves the problem of inconsistent data definitions and "raw table guesses" by creating a centralized context layer where trusted metrics, joins, and business logic are defined once and reused across dashboards, AI agents, and custom data apps.

How it works

The platform uses a "context layer" (defined via dbt projects or YAML) to govern data access and definitions. It integrates with data warehouses (such as BigQuery, Snowflake, and ClickHouse) and allows teams to manage their analytics through a software development lifecycle, using Git, pull requests, and CI/CD for validation. It also provides an MCP server and CLI skills that allow AI coding agents to build and modify charts and dashboards safely.

Who it’s for

It is designed for modern data teams who want to maintain governance over their metrics while enabling business users to explore data using plain English or custom apps, and for developers who prefer a "BI as code" workflow.

Highlights

  • Agentic BI: AI agents that answer questions based on the governed context layer rather than raw data, ensuring accuracy and respecting permissions.
  • BI as Code: Metrics and dashboards are stored as files, allowing them to be version-controlled, reviewed in pull requests, and validated in CI.
  • Data Apps: Ability to generate custom reports, forecasting tools, and customer-facing data products from prompts.
  • Embedded Analytics: An SDK for embedding dashboards and AI agents into other products with row-level security.
  • Broad Warehouse Support: Adapters for major warehouses including Snowflake, BigQuery, Redshift, Databricks, and Postgres.

Related

  • Project
    Canner/WrenAI

    An open-source generative BI engine that provides a governed semantic and AI context layer to enable AI agents to generate trustworthy text-to-SQL answers and dashboards.

  • Project
    rilldata/rill

    An agent-first business intelligence tool that uses BI-as-code and OLAP engines to provide real-time analytics and conversational BI for humans and AI agents.

  • Project
    wanxingai/LightAgent

    LightAgent is an open‑source Python framework for building lightweight, modular LLM‑driven agents. It supports memory (via mem0), tool integration, multi‑agent routing (LightSwarm), deterministic DAG workflows (LightFlow), streaming OpenAI‑compatible APIs, optional durable sessions, trace observability, guard‑rails, human approval hooks, and a tool‑generator for rapid API‑to‑tool conversion. The library works with any OpenAI‑style provider and is released under Apache‑2.0.

  • 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.

  • Dispatch
    Solving the Agentic Data Gap: Introducing Airbyte Agents

    Airbyte Agents introduces a unified context layer and Context Store to reduce API churn and token waste when AI agents interact with multiple operational data sources.