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 permissions are defined once and reused across dashboards, AI agents, and data apps.

How it works

The platform uses a "context layer" (defined via dbt projects or YAML) to establish business logic and access rules. This layer powers several interfaces:

  • AI Agents: Conversational interfaces that answer questions based on the governed context layer rather than raw data.
  • BI as Code: Metrics and dashboards are stored as files, allowing teams to use Git, CI/CD pipelines, and pull requests to validate and ship analytics changes.
  • Data Apps: Custom reporting tools and forecasting products built from prompts using the existing context layer.
  • MCP Server: A Model Context Protocol server that allows coding agents to build charts and metrics directly from a terminal or editor.

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 through plain-English queries and AI-driven applications.

Highlights

  • Governed AI: AI agents respect permissions and return inspectable queries based on verified metrics.
  • Developer-native workflow: Supports a CLI, Git integration, and CI for previewing and validating analytics.
  • Embedded Analytics: An SDK for embedding dashboards and AI agents into other products with row-level security.
  • Multi-warehouse support: Compatible with BigQuery, Snowflake, Redshift, Databricks, Postgres, Trino, and ClickHouse.

Related

  • Project
    Canner/WrenAI

    An open-source generative BI engine that provides a governed semantic layer for AI agents to turn business questions into correct SQL and deployable dashboards.

  • 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
    wanxingai/LightAgent

    LightAgent is an Apache‑2.0‑licensed Python framework for building lightweight, production‑grade LLM agents. It offers built‑in memory (via mem0), tool integration, tree‑of‑thought reasoning, multi‑agent routing (LightSwarm), deterministic workflow orchestration (LightFlow), optional dynamic DAGs, OpenAI‑compatible streaming APIs, structured tracing, guardrails, and human‑approval hooks. Install with `pip install lightagent` and start with a single `LightAgent(...).run(query)` call.

  • 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.

  • 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.