Skip to main content

​
Install the SDK

pip install aden-py python-dotenv

​
With Provider Support

pip install aden-py[openai]

​
Framework Integrations

pip install aden-py[pydantic-ai]

​
Environment Setup

Add to your shell configuration (~/.bashrc or ~/.zshrc): 
export OPENAI_API_KEY=sk-xxx
export ADEN_API_URL=https://kube.acho.io # Use http://localhost:4000 if using self-hosting
export ADEN_API_KEY=your-aden-api-key
Or create a .env file: 
OPENAI_API_KEY=sk-xxx
ADEN_API_URL=https://kube.acho.io # Use http://localhost:4000 if using self-hosting
ADEN_API_KEY=your-aden-api-key
Don’t have an Aden API key yet? You can still use the SDK locally with the console emitter for testing.
If you are using self-hosting, use http://localhost:4000 as the ADEN_API_URL.

​
Requirements

RequirementVersion
Python>= 3.10

​
Optional Dependencies

PackageVersionRequired For
openai>= 1.0.0OpenAI provider
tiktoken>= 0.5.0OpenAI token counting
anthropic>= 0.20.0Anthropic provider
google-generativeai>= 0.4.0Gemini provider
aiohttp>= 3.8.0Async control agent

​
Verify Installation

import os
from dotenv import load_dotenv
load_dotenv()

from aden import instrument, MeterOptions, create_console_emitter, uninstrument

# Instrument the SDK
instrument(MeterOptions(
    emit_metric=create_console_emitter(pretty=True),
))

print("Instrumentation successful!")

# Clean up
uninstrument()
Run the test: 
python test.py

python -m venv .venv
source .venv/bin/activate  # Linux/macOS
.venv\Scripts\activate     # Windows
pip install aden-py[all]

​
Next Steps

Quick Start

Learn how to instrument your first LLM application