Integrations

AutoGen

Build multi-agent LLM applications with AutoGen using DEVUP AI endpoints.

AutoGen is a framework for building LLM applications with multiple agents that converse to solve tasks. It works with DEVUP AI via the OpenAI-compatible API.

Installation

bash

pip install pyautogen

Configuration

Point AutoGen at the DEVUP AI endpoint using base_url:

python

import autogen

config_list = [
    {
        "model": "deepseek-ai/DeepSeek-V3",
        "base_url": "https://api.devupai.com/v1",
        "api_key": "<your DEVUP API key here>"
    }
]

llm_config = {"config_list": config_list, "seed": 42}

assistant = autogen.AssistantAgent("assistant", llm_config=llm_config)
user_proxy = autogen.UserProxyAgent("user_proxy", code_execution_config={"work_dir": "coding"})
user_proxy.initiate_chat(assistant, message="What time is it right now?")

You can use any OpenAI-compatible LLM from DEVUP AI.

How it works

In the example above, two agents converse to solve the task:

The assistant agent generates a Python code snippet to get the current time
The user_proxy agent automatically detects and executes the code block
The result is sent back to the assistant, which summarizes it

Example output:

text

user_proxy (to assistant):

What time is it now?

--------------------------------------------------------------------------------
assistant (to user_proxy):

To get the current time, you can use the `datetime` module in Python...

```python
import datetime
current_time = datetime.datetime.now()
print(current_time.strftime("%I:%M %p"))
```

--------------------------------------------------------------------------------
user_proxy (to assistant):

exitcode: 0 (execution succeeded)
Code output:
02:20 PM

--------------------------------------------------------------------------------
assistant (to user_proxy):

The current time is 02:20 PM.

Anthropic SDK & Claude

Authentication