• Stars
    star
    26,314
  • Rank 726 (Top 0.02 %)
  • Language
    Jupyter Notebook
  • License
    Creative Commons ...
  • Created 9 months ago
  • Updated 1 day ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

PyPI version Build Python Version Downloads

This project is a spinoff from FLAML.

AutoGen

πŸ”₯ Nov 8: AutoGen is selected into Open100: Top 100 Open Source achievements 40 days after release.

πŸ”₯ Nov 6: AutoGen is mentioned by Satya Nadella in a fireside chat around 13:20.

πŸ”₯ Nov 1: AutoGen is the top trending repo on GitHub in October 2023.

πŸ”₯ Heads-up: pyautogen v0.2 will switch to using openai v1. Please read the migration guide.

What is AutoGen

AutoGen is a framework that enables the development of LLM applications using multiple agents that can converse with each other to solve tasks. AutoGen agents are customizable, conversable, and seamlessly allow human participation. They can operate in various modes that employ combinations of LLMs, human inputs, and tools.

AutoGen Overview

  • AutoGen enables building next-gen LLM applications based on multi-agent conversations with minimal effort. It simplifies the orchestration, automation, and optimization of a complex LLM workflow. It maximizes the performance of LLM models and overcomes their weaknesses.
  • It supports diverse conversation patterns for complex workflows. With customizable and conversable agents, developers can use AutoGen to build a wide range of conversation patterns concerning conversation autonomy, the number of agents, and agent conversation topology.
  • It provides a collection of working systems with different complexities. These systems span a wide range of applications from various domains and complexities. This demonstrates how AutoGen can easily support diverse conversation patterns.
  • AutoGen provides enhanced LLM inference. It offers utilities like API unification and caching, and advanced usage patterns, such as error handling, multi-config inference, context programming, etc.

AutoGen is powered by collaborative research studies from Microsoft, Penn State University, and the University of Washington.

Quickstart

The easiest way to start playing is

  1. Click below to use the GitHub Codespace

    Open in GitHub Codespaces

  2. Copy OAI_CONFIG_LIST_sample to ./notebook folder, name to OAI_CONFIG_LIST, and set the correct configuration.

  3. Start playing with the notebooks!

Installation

AutoGen requires Python version >= 3.8, < 3.12. It can be installed from pip:

pip install pyautogen

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

Find more options in Installation.

For code execution, we strongly recommend installing the Python docker package and using docker.

For LLM inference configurations, check the FAQs.

Multi-Agent Conversation Framework

Autogen 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: AutoGen 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: AutoGen 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: AutoGen seamlessly allows human participation. This means that humans can provide input and feedback to the agents as needed.

For example,

from autogen import AssistantAgent, UserProxyAgent, config_list_from_json
# Load LLM inference endpoints from an env variable or a file
# See https://microsoft.github.io/autogen/docs/FAQ#set-your-api-endpoints
# and OAI_CONFIG_LIST_sample
config_list = config_list_from_json(env_or_file="OAI_CONFIG_LIST")
# You can also set config_list directly as a list, for example, config_list = [{'model': 'gpt-4', 'api_key': '<your OpenAI API key here>'},]
assistant = AssistantAgent("assistant", llm_config={"config_list": config_list})
user_proxy = UserProxyAgent("user_proxy", code_execution_config={"work_dir": "coding"})
user_proxy.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 test/twoagent.py

After the repo is cloned. The figure below shows an example conversation flow with AutoGen. Agent Chat Example

Please find more code examples for this feature.

Enhanced LLM Inferences

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

Documentation

You can find detailed documentation about AutoGen here.

In addition, you can find:

Citation

AutoGen

@inproceedings{wu2023autogen,
      title={AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework},
      author={Qingyun Wu and Gagan Bansal and Jieyu Zhang and Yiran Wu and Shaokun Zhang and Erkang Zhu and Beibin Li and Li Jiang and Xiaoyun Zhang and Chi Wang},
      year={2023},
      eprint={2308.08155},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}

EcoOptiGen

@inproceedings{wang2023EcoOptiGen,
    title={Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference},
    author={Chi Wang and Susan Xueqing Liu and Ahmed H. Awadallah},
    year={2023},
    booktitle={AutoML'23},
}

MathChat

@inproceedings{wu2023empirical,
    title={An Empirical Study on Challenging Math Problem Solving with GPT-4},
    author={Yiran Wu and Feiran Jia and Shaokun Zhang and Hangyu Li and Erkang Zhu and Yue Wang and Yin Tat Lee and Richard Peng and Qingyun Wu and Chi Wang},
    year={2023},
    booktitle={ArXiv preprint arXiv:2306.01337},
}

Contributing

This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

If you are new to GitHub here is a detailed help source on getting involved with development on GitHub.

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information, see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.

Contributors Wall

Legal Notices

Microsoft and any contributors grant you a license to the Microsoft documentation and other content in this repository under the Creative Commons Attribution 4.0 International Public License, see the LICENSE file, and grant you a license to any code in the repository under the MIT License, see the LICENSE-CODE file.

Microsoft, Windows, Microsoft Azure, and/or other Microsoft products and services referenced in the documentation may be either trademarks or registered trademarks of Microsoft in the United States and/or other countries. The licenses for this project do not grant you rights to use any Microsoft names, logos, or trademarks. Microsoft's general trademark guidelines can be found at http://go.microsoft.com/fwlink/?LinkID=254653.

Privacy information can be found at https://privacy.microsoft.com/en-us/

Microsoft and any contributors reserve all other rights, whether under their respective copyrights, patents, or trademarks, whether by implication, estoppel, or otherwise.

More Repositories

1

vscode

Visual Studio Code
TypeScript
157,226
star
2

PowerToys

Windows system utilities to maximize productivity
C#
105,072
star
3

TypeScript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TypeScript
98,425
star
4

terminal

The new Windows Terminal and the original Windows console host, all in the same place!
C++
93,068
star
5

Web-Dev-For-Beginners

24 Lessons, 12 Weeks, Get Started as a Web Developer
JavaScript
81,753
star
6

ML-For-Beginners

12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
HTML
67,415
star
7

playwright

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.
TypeScript
61,636
star
8

generative-ai-for-beginners

18 Lessons, Get Started Building with Generative AI πŸ”— https://microsoft.github.io/generative-ai-for-beginners/
Jupyter Notebook
44,178
star
9

monaco-editor

A browser based code editor
JavaScript
35,437
star
10

AI-For-Beginners

12 Weeks, 24 Lessons, AI for All!
Jupyter Notebook
31,919
star
11

MS-DOS

The original sources of MS-DOS 1.25, 2.0, and 4.0 for reference purposes
Assembly
28,654
star
12

calculator

Windows Calculator: A simple yet powerful calculator that ships with Windows
C++
27,371
star
13

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Python
26,923
star
14

Data-Science-For-Beginners

10 Weeks, 20 Lessons, Data Science for All!
Jupyter Notebook
26,675
star
15

cascadia-code

This is a fun, new monospaced font that includes programming ligatures and is designed to enhance the modern look and feel of the Windows Terminal.
Python
24,504
star
16

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
Python
22,801
star
17

api-guidelines

Microsoft REST API Guidelines
22,345
star
18

winget-cli

WinGet is the Windows Package Manager. This project includes a CLI (Command Line Interface), PowerShell modules, and a COM (Component Object Model) API (Application Programming Interface).
C++
20,495
star
19

vcpkg

C++ Library Manager for Windows, Linux, and MacOS
CMake
19,600
star
20

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Python
18,340
star
21

semantic-kernel

Integrate cutting-edge LLM technology quickly and easily into your apps
C#
17,792
star
22

fluentui

Fluent UI web represents a collection of utilities, React components, and web components for building web applications.
TypeScript
17,772
star
23

CNTK

Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
C++
17,412
star
24

WSL

Issues found on WSL
PowerShell
16,746
star
25

LightGBM

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.
C++
16,136
star
26

recommenders

Best Practices on Recommendation Systems
Python
16,075
star
27

react-native-windows

A framework for building native Windows apps with React.
C++
16,005
star
28

AirSim

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
C++
15,836
star
29

IoT-For-Beginners

12 Weeks, 24 Lessons, IoT for All!
C++
14,771
star
30

qlib

Qlib is an AI-oriented quantitative investment platform that aims to realize the potential, empower research, and create value using AI technologies in quantitative investment, from exploring ideas to implementing productions. Qlib supports diverse machine learning modeling paradigms. including supervised learning, market dynamics modeling, and RL.
Python
14,319
star
31

Bringing-Old-Photos-Back-to-Life

Bringing Old Photo Back to Life (CVPR 2020 oral)
Python
14,132
star
32

dotnet

This repo is the official home of .NET on GitHub. It's a great starting point to find many .NET OSS projects from Microsoft and the community, including many that are part of the .NET Foundation.
HTML
14,091
star
33

nni

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
Python
13,084
star
34

ai-edu

AI education materials for Chinese students, teachers and IT professionals.
HTML
13,046
star
35

pyright

Static Type Checker for Python
Python
11,969
star
36

guidance

A guidance language for controlling large language models.
Jupyter Notebook
11,777
star
37

TypeScript-Node-Starter

A reference example for TypeScript and Node with a detailed README describing how to use the two together.
SCSS
11,258
star
38

Swin-Transformer

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".
Python
11,187
star
39

TypeScript-React-Starter

A starter template for TypeScript and React with a detailed README describing how to use the two together.
TypeScript
11,081
star
40

frontend-bootcamp

Frontend Workshop from HTML/CSS/JS to TypeScript/React/Redux
TypeScript
10,795
star
41

language-server-protocol

Defines a common protocol for language servers.
HTML
10,093
star
42

windows-rs

Rust for Windows
Rust
9,918
star
43

onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
C++
9,837
star
44

wslg

Enabling the Windows Subsystem for Linux to include support for Wayland and X server related scenarios
C++
9,764
star
45

sql-server-samples

Azure Data SQL Samples - Official Microsoft GitHub Repository containing code samples for SQL Server, Azure SQL, Azure Synapse, and Azure SQL Edge
9,520
star
46

mimalloc

mimalloc is a compact general purpose allocator with excellent performance.
C
9,505
star
47

computervision-recipes

Best Practices, code samples, and documentation for Computer Vision.
Jupyter Notebook
9,264
star
48

napajs

Napa.js: a multi-threaded JavaScript runtime
C++
9,256
star
49

Windows-universal-samples

API samples for the Universal Windows Platform.
JavaScript
9,253
star
50

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
Python
9,145
star
51

fast

The adaptive interface system for modern web experiences.
TypeScript
9,041
star
52

vscode-tips-and-tricks

Collection of helpful tips and tricks for VS Code.
9,038
star
53

playwright-python

Python version of the Playwright testing and automation library.
Python
8,990
star
54

STL

MSVC's implementation of the C++ Standard Library.
C++
8,978
star
55

fluentui-emoji

A collection of familiar, friendly, and modern emoji from Microsoft
Python
8,678
star
56

react-native-code-push

React Native module for CodePush
C
8,643
star
57

reactxp

Library for cross-platform app development.
TypeScript
8,298
star
58

reverse-proxy

A toolkit for developing high-performance HTTP reverse proxy applications.
C#
8,121
star
59

vscode-extension-samples

Sample code illustrating the VS Code extension API.
TypeScript
8,063
star
60

inshellisense

IDE style command line auto complete
TypeScript
8,034
star
61

c9-python-getting-started

Sample code for Channel 9 Python for Beginners course
Jupyter Notebook
7,642
star
62

ailab

Experience, Learn and Code the latest breakthrough innovations with Microsoft AI
C#
7,623
star
63

cpprestsdk

The C++ REST SDK is a Microsoft project for cloud-based client-server communication in native code using a modern asynchronous C++ API design. This project aims to help C++ developers connect to and interact with services.
C++
7,573
star
64

WSL2-Linux-Kernel

The source for the Linux kernel used in Windows Subsystem for Linux 2 (WSL2)
C
7,527
star
65

botframework-sdk

Bot Framework provides the most comprehensive experience for building conversation applications.
JavaScript
7,378
star
66

azuredatastudio

Azure Data Studio is a data management and development tool with connectivity to popular cloud and on-premises databases. Azure Data Studio supports Windows, macOS, and Linux, with immediate capability to connect to Azure SQL and SQL Server. Browse the extension library for more database support options including MySQL, PostreSQL, and MongoDB.
TypeScript
7,182
star
67

winget-pkgs

The Microsoft community Windows Package Manager manifest repository
6,981
star
68

Windows-driver-samples

This repo contains driver samples prepared for use with Microsoft Visual Studio and the Windows Driver Kit (WDK). It contains both Universal Windows Driver and desktop-only driver samples.
C
6,603
star
69

winfile

Original Windows File Manager (winfile) with enhancements
C
6,437
star
70

nlp-recipes

Natural Language Processing Best Practices & Examples
Python
6,334
star
71

WinObjC

Objective-C for Windows
C
6,237
star
72

SandDance

Visually explore, understand, and present your data.
TypeScript
6,091
star
73

GSL

Guidelines Support Library
C++
5,957
star
74

VFSForGit

Virtual File System for Git: Enable Git at Enterprise Scale
C#
5,945
star
75

MixedRealityToolkit-Unity

This repository is for the legacy Mixed Reality Toolkit (MRTK) v2. For the latest version of the MRTK please visit https://github.com/MixedRealityToolkit/MixedRealityToolkit-Unity
C#
5,943
star
76

vscode-go

An extension for VS Code which provides support for the Go language. We have moved to https://github.com/golang/vscode-go
TypeScript
5,931
star
77

microsoft-ui-xaml

Windows UI Library: the latest Windows 10 native controls and Fluent styles for your applications
5,861
star
78

vscode-recipes

JavaScript
5,802
star
79

MMdnn

MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.
Python
5,782
star
80

ethr

Ethr is a Comprehensive Network Measurement Tool for TCP, UDP & ICMP.
Go
5,642
star
81

FASTER

Fast persistent recoverable log and key-value store + cache, in C# and C++.
C#
5,630
star
82

rushstack

Monorepo for tools developed by the Rush Stack community
TypeScript
5,629
star
83

fluentui-system-icons

Fluent System Icons are a collection of familiar, friendly and modern icons from Microsoft.
HTML
5,505
star
84

vscode-docs

Public documentation for Visual Studio Code
Markdown
5,477
star
85

DirectX-Graphics-Samples

This repo contains the DirectX Graphics samples that demonstrate how to build graphics intensive applications on Windows.
C++
5,440
star
86

vscode-cpptools

Official repository for the Microsoft C/C++ extension for VS Code.
TypeScript
5,357
star
87

BosqueLanguage

The Bosque programming language is an experiment in regularized design for a machine assisted rapid and reliable software development lifecycle.
TypeScript
5,282
star
88

DeepSpeedExamples

Example models using DeepSpeed
Python
5,092
star
89

promptbase

All things prompt engineering
Python
5,012
star
90

Detours

Detours is a software package for monitoring and instrumenting API calls on Windows. It is distributed in source code form.
C++
4,889
star
91

TypeScript-Handbook

Deprecated, please use the TypeScript-Website repo instead
JavaScript
4,881
star
92

Windows-classic-samples

This repo contains samples that demonstrate the API used in Windows classic desktop applications.
4,824
star
93

tsyringe

Lightweight dependency injection container for JavaScript/TypeScript
TypeScript
4,778
star
94

TaskWeaver

A code-first agent framework for seamlessly planning and executing data analytics tasks.
Python
4,679
star
95

vscode-dev-containers

NOTE: Most of the contents of this repository have been migrated to the new devcontainers GitHub org (https://github.com/devcontainers). See https://github.com/devcontainers/template-starter and https://github.com/devcontainers/feature-starter for information on creating your own!
Shell
4,678
star
96

tsdoc

A doc comment standard for TypeScript
TypeScript
4,657
star
97

FluidFramework

Library for building distributed, real-time collaborative web applications
TypeScript
4,611
star
98

SPTAG

A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario.
C++
4,603
star
99

WPF-Samples

Repository for WPF related samples
C#
4,545
star
100

TypeScript-Vue-Starter

A starter template for TypeScript and Vue with a detailed README describing how to use the two together.
JavaScript
4,458
star