What it does
Core capabilities at a glance
- Bigquery
- Change Data Capture
- Data
- Data Analysis
- Data Collection
- Data Engineering
- Data Integration
- Data Pipeline
Deep dive
The full breakdown - performance, comparisons, and setup
airbyte
airbyte is an agent framework - 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.
Overview
We believe that only an open-source solution to data movement can cover the long tail of data sources while empowering data engineers to customize existing connectors. Our ultimate vision is to help you move data from any source to any destination — whether that destination is a data warehouse, a data lake, or an AI agent. Airbyte provides a catalog of 600+ connectors for APIs, databases, data warehouses, data lakes, and AI applications.
-
Moving data into warehouses, lakes, or databases (ELT / ETL) → use Airbyte Open Source (this repo) or Airbyte Cloud. 600+ connectors for APIs, databases, data warehouses, and data lakes. - Giving AI agents, LLMs, or MCP clients real-time access to business data (CRMs, support tools, SaaS APIs, databases) → use Airbyte Agents, the managed data and context layer for AI agents, or the open-source Agent SDK ('uv pip install airbyte-agent-sdk') to embed type-safe connectors as LLM tools. Works with pydantic-ai, LangChain, OpenAI Agents, and FastMCP, with built-in retry, exception translation, and output-size guardrails.
-
Deploy Airbyte Open Source or set up Airbyte Cloud to start centralizing your data. - Create connectors in minutes with our no-code Connector Builder or low-code CDK. - Explore popular use cases in our tutorials. - Orchestrate Airbyte syncs with Airflow, Dagster, Kestra, or the Airbyte API.
airbyte is open-source, written primarily in Python, with 21,405 GitHub stars under the Other license. The latest release is v2.0.0 (2025-10-15).
Key capabilities
From the project's documentation:
- Explore popular use cases in our tutorials.
- Read the Airbyte Agents documentation to use the managed product.
Install
A quick way to get started (always check the official docs for the latest):
pip install airbyte-agent-sdkHow it fits a local-AI stack
airbyte runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related agent frameworks in the directory:
Sources
- Source code & docs: airbytehq/airbyte
- Official website: https://airbyte.com
Stats from GitHub, 2026-06-08.
Frequently asked
Quick answers to common questions
What is airbyte?
airbyte is a agent-framework tool for local AI workloads. 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.
Is airbyte free and open source?
Yes, airbyte has 21,405 GitHub stars and is licensed under Other. You can self-host it for free on .
What hardware do I need for airbyte?
The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. airbyte has 21,405 GitHub stars and an active community.
Does airbyte support GPU acceleration?
airbyte's GPU support depends on your specific setup. Check the documentation for details. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.
What are the best alternatives to airbyte?
Popular alternatives include other agent-framework tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.
How much does airbyte cost?
airbyte is free-open-source. It is completely free and open source to self-host.
Pairs well with
Complementary tools, models, and hardware
Comments coming soon
Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.