airbytehq/airbyte

Open-source data movement for ELT pipelines and AI agents — from APIs, databases & files to warehouses, lakes, and AI applications. Both self-hosted and Cloud.

What it solves

Airbyte simplifies the process of moving data from a wide variety of sources to various destinations. It addresses the challenge of covering a "long tail" of data sources by providing an open-source framework that allows users to move data into warehouses, lakes, and databases, or provide real-time business data to AI agents and LLMs.

How it works

Airbyte uses a vast catalog of over 600 connectors to bridge the gap between APIs, databases, and files and their final destinations. For traditional ELT (Extract, Load, Transform) pipelines, it centralizes data into warehouses or lakes. For AI applications, it offers an Agent SDK that allows developers to embed these connectors as type-safe tools for LLMs, integrating with frameworks like LangChain and pydantic-ai.

Who it’s for

It is designed for data engineers who need to build and manage data pipelines, as well as AI developers building agents that require real-time access to business data from CRMs, SaaS APIs, and databases.

Highlights

  • Over 600 pre-built connectors for diverse data sources and destinations.
  • No-code Connector Builder and low-code CDK for creating custom connectors quickly.
  • Integration with orchestration tools like Airflow, Dagster, and Kestra.
  • Dedicated Agent SDK for turning data connectors into LLM tools with built-in guardrails and retry logic.

Related

  • 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
    airweave-ai/airweave

    An open-source context retrieval layer for AI agents and RAG systems that syncs data from 50+ integrations into a unified, LLM-friendly search interface.

  • Project
    airbytehq/PyAirbyte

    A Python library that enables developers to use Airbyte connectors directly in Python for data movement and ETL pipelines without needing the full Airbyte platform.

  • Project
    agentgateway/agentgateway

    An open-source proxy providing security, observability, and governance for communications between AI agents, LLMs, and tools using MCP and A2A protocols.

  • Project
    countbot-ai/CountBot

    An open-source AI Agent framework and hub that connects LLMs, multiple IM channels, and external tools for long-term local deployment and task execution.