wangtao
/
autogen
mirror of https://github.com/microsoft/autogen.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
447 Commits 107 Branches 72 Tags 2.2 GiB
Jupyter Notebook 28.1%
Python 27.3%
C# 24.3%
HTML 16.5%
TypeScript 2.9%
Other 0.7%
Go to file
Eric Zhu 976a7d4d77 create model context component, remove chat memory component, refactor samples #454 (#469) 
* create model context component, remove chat memory component, refactor samples #454

* Fix bugs in samples.

* Fix

* Update docs

* add unit tests
 		2024-09-11 14:35:35 -07:00
.devcontainer Marketing sample migration to AGNext (#234) 2024-07-19 20:57:13 +00:00
.github/workflows Require lockfile to be up to date in CI (#457) 2024-09-09 09:34:06 -04:00
docs/design Initial design proposal for message routing (#245) 2024-08-23 13:31:26 -04:00
dotnet Support datacontenttype and lay groundwork for unknown payloads (#444) 2024-09-05 16:36:59 -04:00
protos Support datacontenttype and lay groundwork for unknown payloads (#444) 2024-09-05 16:36:59 -04:00
python create model context component, remove chat memory component, refactor samples #454 (#469) 2024-09-11 14:35:35 -07:00
CHANGELOG.md update readme and add `CHANGELOG.md` (#368) 2024-08-17 06:05:18 +00:00
CODE_OF_CONDUCT.md CODE_OF_CONDUCT.md committed 2024-05-07 15:12:54 -07:00
LICENSE LICENSE committed 2024-05-07 15:12:54 -07:00
README.md Update README.md (#458) 2024-09-09 09:12:27 -07:00
SECURITY.md SECURITY.md committed 2024-05-07 15:12:56 -07:00
SUPPORT.md SUPPORT.md committed 2024-05-07 15:12:55 -07:00

README.md

AGNext (Starfleet)

AGNext is a OSS framework for developing intelligent applications using AI Agents patterns. It offers an easy way to quickly build event-driven, distributed, scalable, resilient AI agent systems. Agents are developed by using the Actor model.

You can build and run your agent system locally and easily move to a distributed system in the cloud when you are ready.

Key Aspects

  • Asynchronous messaging: Agents communicate with each other through asynchronous messages, enabling event-driven and request/response communication models.
  • Scalable & Distributed: Enable complex scenarios with networks of agents across org boundaries
  • Modular, extensible & highly customizable: E.g. custom agents, memory as a service, tools registry, model library
  • x-lang support: Python & Dotnet interoperating agents today, others coming soon
  • Observable, traceable & debuggable

Getting Started

We are in the early stages of development, but we are excited to share our progress with you. We are looking for feedback and contributions to help shape the future of this project. Your best place to start is the Documentation.