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 solves the challenge of moving data between disparate systems. It provides a unified way to sync data from hundreds of sources—such as APIs, databases, and SaaS tools—into data warehouses, lakes, or directly into AI applications and LLM-powered agents.

How it works

It functions as an ELT (Extract, Load, Transform) platform. You configure connectors to pull data from a source and push it to a destination. For AI use cases, it offers an Agent SDK that allows developers to embed these connectors as type-safe tools for LLMs. This SDK handles the complexities of data retrieval, such as retries, exception translation, and output-size guardrails, making it compatible with frameworks like LangChain, Pydantic-AI, and OpenAI Agents.

Who it’s for

It is designed for data engineers building robust data pipelines and AI developers who need to provide their agents with real-time, reliable access to business data stored in external systems.

Highlights

  • Over 600 pre-built connectors for various APIs, databases, and cloud services.
  • No-code Connector Builder and low-code CDK to create custom data integrations quickly.
  • Dedicated Agent SDK to turn data connectors into LLM-ready tools.
  • Built-in support for orchestration via tools like Airflow, Dagster, and Kestra.
  • Enterprise-ready features for data movement, including security and scalability.

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
    agentgateway/agentgateway

    An open-source proxy that provides security, observability, and governance for agent-to-LLM, agent-to-tool, and agent-to-agent communication.

  • Project
    inclusionAI/Avernet

    Avernet is an open‑source platform that lets multiple AI agents—running on different runtimes or existing bot services—join a single, coordinated network. It provides identity, authentication, discovery, routing, and workflow tools (TaskGuard) plus diagnostics/evolution (AgentEvolve). Designed for enterprises needing persistent, governed multi‑agent systems, it ships with a Rust‑based Bot Coordination Service, web workbench, and plugins (e.g., DeepSeek Harness). Core networking features are public; advanced permission, audit, and large‑scale clustering are still in progress.

  • Project
    airbytehq/PyAirbyte

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