AgentLoop

Cite paper.. <!--

:tada: IMPORTANT

:fire: :tada: Nov 11, 2024: We are evolving AutoGen into AgentLoop! A new organization AgentLoopAI is created to host the development of AgentLoop and related projects with open governance. Check AgentLoop's new look.

We invite collaborators from all organizations and individuals to join the development.

:fire: :tada: AgentLoop is available via pyautogen (or its alias autogen or agentloop) on PyPI!

pip install pyautogen

License: We adopt the Apache 2.0 license from v0.3. This enhances our commitment to open-source collaboration while providing additional protections for contributors and users alike.

:tada: May 29, 2024: DeepLearning.ai launched a new short course AI Agentic Design Patterns with AutoGen, made in collaboration with Microsoft and Penn State University, and taught by AutoGen creators Chi Wang and Qingyun Wu.

:tada: May 24, 2024: Foundation Capital published an article on Forbes: The Promise of Multi-Agent AI and a video AI in the Real World Episode 2: Exploring Multi-Agent AI and AutoGen with Chi Wang.

:tada: May 13, 2024: The Economist published an article about multi-agent systems (MAS) following a January 2024 interview with Chi Wang.

:tada: May 11, 2024: AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation received the best paper award at the ICLR 2024 LLM Agents Workshop.

:tada: Apr 17, 2024: Andrew Ng cited AutoGen in The Batch newsletter and What's next for AI agentic workflows at Sequoia Capital's AI Ascent (Mar 26).

:tada: Mar 3, 2024: What's new in AutoGen? Blog; Youtube.

:tada: Dec 31, 2023: AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework is selected by TheSequence: My Five Favorite AI Papers of 2023.

:tada: Nov 8, 2023: AutoGen is selected into Open100: Top 100 Open Source achievements 35 days after spinoff from FLAML.

:tada: Mar 29, 2023: AutoGen is first created in FLAML.

What is AgentLoop

AgentLoop (formerly AutoGen) is an open-source programming framework for building AI agents and facilitating cooperation among multiple agents to solve tasks. AgentLoop aims to streamline the development and research of agentic AI, much like PyTorch does for Deep Learning. It offers features such as agents capable of interacting with each other, facilitates the use of various large language models (LLMs) and tool use support, autonomous and human-in-the-loop workflows, and multi-agent conversation patterns.

Open Source Statement: The project welcomes contributions from developers and organizations worldwide. Our goal is to foster a collaborative and inclusive community where diverse perspectives and expertise can drive innovation and enhance the project's capabilities. Whether you are an individual contributor or represent an organization, we invite you to join us in shaping the future of this project. Together, we can build something truly remarkable.

The project is currently maintained by a dynamic group of volunteers from several organizations. Contact project administrators Chi Wang and Qingyun Wu via support@agentloop.xyz if you are interested in becoming a maintainer.

Back to Top

Quickstart

The easiest way to start playing is 1. Click below to use the GitHub Codespace

[![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/agentloopai/agentloop?quickstart=1)

1. Copy OAICONFIGLISTsample to ./notebook folder, name to OAICONFIG_LIST, and set the correct configuration.
2. Start playing with the notebooks!

NOTE: OAICONFIGLIST_sample lists gpt-4o as the default model. If you use a different model, you may need to revise various system prompts (especially if using weaker models like gpt-4o-mini). Proceed with caution when updating this default and be aware of additional risks related to alignment and safety.

Back to Top

Option 1. Install and Run AgentLoop in Docker

Find detailed instructions for users here, and for developers here.

Option 2. Install AgentLoop Locally

AgentLoop requires Python version >= 3.9, < 3.14. It can be installed from pip:

bash pip install agentloop

Minimal dependencies are installed without extra options. You can install extra options based on the feature you need.

Find more options in Installation.

Even if you are installing and running AgentLoop locally outside of docker, the recommendation and default behavior of agents is to perform code execution in docker. Find more instructions and how to change the default behaviour here.

For LLM inference configurations, check the FAQs.

Back to Top

Multi-Agent Conversation Framework

AgentLoop enables the next-gen LLM applications with a generic multi-agent conversation framework. It offers customizable and conversable agents that integrate LLMs, tools, and humans. By automating chat among multiple capable agents, one can easily make them collectively perform tasks autonomously or with human feedback, including tasks that require using tools via code.

Features of this use case include:

• Multi-agent conversations: AgentLoop agents can communicate with each other to solve tasks. This allows for more complex and sophisticated applications than would be possible with a single LLM.
• Customization: AgentLoop agents can be customized to meet the specific needs of an application. This includes the ability to choose the LLMs to use, the types of human input to allow, and the tools to employ.
• Human participation: AgentLoop seamlessly allows human participation. This means that humans can provide input and feedback to the agents as needed.

For example,

```python from autogen import AssistantAgent, UserProxyAgent, configlistfrom_json

Load LLM inference endpoints from an env variable or a file

See https://docs.agentloop.ai/docs/FAQ#set-your-api-endpoints

and OAICONFIGLIST_sample

configlist = configlistfromjson(envorfile="OAICONFIGLIST")

You can also set configlist directly as a list, for example, configlist = [{'model': 'gpt-4o', 'api_key': ''},]

assistant = AssistantAgent("assistant", llmconfig={"configlist": configlist}) userproxy = UserProxyAgent("userproxy", codeexecutionconfig={"workdir": "coding", "usedocker": False}) # IMPORTANT: set to True to run code in docker, recommended userproxy.initiate_chat(assistant, message="Plot a chart of NVDA and TESLA stock price change YTD.")

This initiates an automated chat between the two agents to solve the task

```

This example can be run with

python python test/twoagent.py

After the repo is cloned. The figure below shows an example conversation flow with AgentLoop.

Alternatively, the sample code here allows a user to chat with an AgentLoop agent in ChatGPT style. Please find more code examples for this feature.

Back to Top

Enhanced LLM Inferences

AgentLoop also helps maximize the utility out of the expensive LLMs such as gpt-4o. It offers enhanced LLM inference with powerful functionalities like caching, error handling, multi-config inference and templating.

Back to Top

Documentation

You can find detailed documentation about AgentLoop here.

In addition, you can find:

• Research, blogposts around AgentLoop, and [Transparency FAQs](https://github.com/