🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.
# Airbyte SDK
Type-safe connector execution framework with blessed connectors and full IDE autocomplete.
## Overview
The Airbyte SDK executes connector operations through the Airbyte platform. The platform manages third-party API credentials, handles rate limiting, and provides a unified execution layer.
## Installation
```bash
uv pip install airbyte-agent-sdk
```
## Credentials
You need Airbyte platform credentials to use the SDK:
- **`AIRBYTE_CLIENT_ID`** / **`AIRBYTE_CLIENT_SECRET`** — from your Airbyte Cloud organization settings
- **`connector_id`** — the source UUID for an existing connector (from the Airbyte dashboard or `create()`)
## Quick Start: Connect to an Existing Source
```python
from airbyte_agent_sdk.connectors.stripe import StripeConnector
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = StripeConnector(auth_config=AirbyteAuthConfig(
airbyte_client_id="your_client_id",
airbyte_client_secret="your_client_secret",
connector_id="your_source_uuid",
))
# List customers — returns typed Pydantic envelope
customers = await connector.customers.list(limit=10)
for c in customers.data:
print(f"{c.id}: {c.email}")
print(f"More pages? {customers.meta.has_more}")
# Get a single customer
customer = await connector.customers.get(id="cus_123")
print(customer["email"])
# Health check
check = await connector.check()
print(check.status) # "healthy"
```
## Getting Started: Create a New Source
Use `StripeConnector.create()` to provision a source on Airbyte Cloud:
```python
from airbyte_agent_sdk.connectors.stripe import StripeConnector
from airbyte_agent_sdk.connectors.stripe.models import StripeAuthConfig
from airbyte_agent_sdk.types import AirbyteAuthConfig
connector = await StripeConnector.create(
airbyte_config=AirbyteAuthConfig(
airbyte_client_id="your_client_id",
airbyte_client_secret="your_client_secret",
workspace_name="my-workspace",
),
auth_config=StripeAuthConfig(api_key="sGoogle's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.