A comprehensive data infrastructure for replication and AI agents

As teams build AI applications and agentic workflows, they need reliable access to real-time context across systems. Airbyte offers a growing set of agent-native connectors: standalone Python SDKs designed for real-time fetch and search operations, with write and trigger operations coming soon. These connectors provide:

• 10+ agent connectors available as individual Python SDKs (releasing new connectors weekly)
• Strongly-typed, well-documented access to third-party APIs
• Real-time read access to systems like Salesforce, HubSpot, GitHub, Jira, Stripe, Zendesk, Gong, and more
• MCP interface compatible with modern agent platforms
• Built on PydanticAI and compatible with LangChain, LlamaIndex, and other AI libraries. PydanticAI, LangChain, LlamaIndex) and MCP standard

Airbyte provides the infrastructure for building extract-and-load pipelines from APIs, databases, and files into databases, warehouses, and lakes. It is designed for versatility, scalability, and ease of use. The replication connector catalog includes:

• 600+ pre-built replication and agent connectors: Airbyte’s connector catalog comes “out-of-the-box” with over 600 connectors. These connectors can be used to start replicating data from a source to a destination in just a few minutes.
• No-Code Connector Builder: You can easily extend Airbyte’s functionality to support your custom use cases through tools like the No-Code Connector Builder.
• The platform: Airbyte’s platform provides all the horizontal services required to configure and scale data movement operations, available as cloud-managed or self-managed.
• The user interface: Airbyte features a UI, PyAirbyte (Python library), API, and Terraform Provider to integrate with your preferred tooling and approach to infrastructure management. Airbyte is suitable for a wide range of data integration use cases, including AI data infrastructure and EL(T) workloads. Airbyte is also embeddable within your own application or platform to power your product.

This foundation is battle-tested in production across thousands of companies and supported by a community of over 27,000 developers.

• Airbyte Cloud - A hosted service that allows you to focus on moving data while we take care of managing the infrastructure
• Airbyte Open-Source - Deploy on your own infrastructure and start moving data
• Airbyte Embedded - Airbyte Embedded enables you to add hundreds of data integrations into your product, allowing end-users to authenticate their sources and sync data to your warehouse

Highlighted below are the main repositories. We accept community contributions to the Airbyte repo.

• airbyte-agent-connectors - Python SDKs for use in your app, an agent framework, or MCP
• Airbyte - all Airbyte replication connectors, Airbyte CDK and Airbyte CI tools
• abctl - Command line tool to deploy Airbyte locally or to any single node physical or virtual machine
• Airbyte Platform - the data replication platform
• Airbyte Protocol - describes a series of standard components and all the interactions between them in order to declare an ELT pipeline

• Terraform - declaratively version Airbyte Connectors as code.
• Helm Charts - run Airbyte at scale on Kubernetes.
• pyAirbyte - use Airbyte connectors directly in Python without the Airbyte Platform.
• Airbyte REST API - Programmatically control Airbyte Cloud through an API.