From ecdf18d3f6ae406bb96859358e94edf9eee4ea06 Mon Sep 17 00:00:00 2001 From: Jack Gerrits Date: Thu, 9 Jan 2025 13:44:13 -0500 Subject: [PATCH] Make package readmes slightly less empty (#4961) * Make package readmes slightly less empty * Update python/packages/autogen-ext/README.md --------- Co-authored-by: Eric Zhu --- python/packages/autogen-agentchat/README.md | 9 +++++++++ python/packages/autogen-core/README.md | 2 ++ python/packages/autogen-ext/README.md | 6 ++++-- 3 files changed, 15 insertions(+), 2 deletions(-) diff --git a/python/packages/autogen-agentchat/README.md b/python/packages/autogen-agentchat/README.md index 07fa5d8c5..4ada6f982 100644 --- a/python/packages/autogen-agentchat/README.md +++ b/python/packages/autogen-agentchat/README.md @@ -1,3 +1,12 @@ # AutoGen AgentChat - [Documentation](https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html) + +AgentChat is a high-level API for building multi-agent applications. +It is built on top of the [`autogen-core`](https://microsoft.github.io/autogen/stable/user-guide/core-user-guide/index.html) package. +For beginner users, AgentChat is the recommended starting point. +For advanced users, [`autogen-core`](https://microsoft.github.io/autogen/stable/user-guide/core-user-guide/index.html)'s event-driven +programming model provides more flexibility and control over the underlying components. + +AgentChat provides intuitive defaults, such as **Agents** with preset +behaviors and **Teams** with predefined [multi-agent design patterns](https://microsoft.github.io/autogen/stable/user-guide/core-user-guide/design-patterns/intro.html). diff --git a/python/packages/autogen-core/README.md b/python/packages/autogen-core/README.md index b09e22b90..8cebb6169 100644 --- a/python/packages/autogen-core/README.md +++ b/python/packages/autogen-core/README.md @@ -1,3 +1,5 @@ # AutoGen Core - [Documentation](https://microsoft.github.io/autogen/stable/user-guide/core-user-guide/index.html) + +AutoGen core offers an easy way to quickly build event-driven, distributed, scalable, resilient AI agent systems. Agents are developed by using the [Actor model](https://en.wikipedia.org/wiki/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. diff --git a/python/packages/autogen-ext/README.md b/python/packages/autogen-ext/README.md index 402c411e2..99f3138df 100644 --- a/python/packages/autogen-ext/README.md +++ b/python/packages/autogen-ext/README.md @@ -1,3 +1,5 @@ -# autogen-ext +# AutoGen Extensions -[Documentation](https://microsoft.github.io/autogen/stable/user-guide/extensions-user-guide/index.html) +- [Documentation](https://microsoft.github.io/autogen/stable/user-guide/extensions-user-guide/index.html) + +AutoGen is designed to be extensible. The `autogen-ext` package contains many different component implementations maintained by the AutoGen project. However, we strongly encourage others to build their own components and publish them as part of the ecosytem.