wangtao
/
autogen
mirror of https://github.com/microsoft/autogen.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
434 Commits 177 Branches 98 Tags 320 MiB
Jupyter Notebook 33.7%
Python 31.8%
C# 26.8%
TypeScript 6.8%
HTML 0.3%
Other 0.4%
Go to file
Aamir dacd290f1e Add a generic `stop_when` to runtime (#431) 
* Add stop_when

* Format

---------

Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
 		2024-08-30 15:28:51 -04:00
.devcontainer Marketing sample migration to AGNext (#234) 2024-07-19 20:57:13 +00:00
.github/workflows Migrate to uv and poe for workspace management and task running (#424) 2024-08-29 09:46:06 -04:00
docs/design Initial design proposal for message routing (#245) 2024-08-23 13:31:26 -04:00
dotnet Update aspire version (#437) 2024-08-30 09:53:20 -04:00
protos Implement RPC and Subscription-based broadcast for python host and worker runtime. (#389) 2024-08-22 16:07:28 +00:00
python Add a generic `stop_when` to runtime (#431) 2024-08-30 15:28:51 -04:00
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 and add `CHANGELOG.md` (#368) 2024-08-17 06:05:18 +00:00
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.