Earlier this week, Microsoft introduced the Agent Framework to its open source project Semantic Kernel, an SDK that integrates LLMs with C#, Python, and Java so that developers can incorporate AI features into their apps.
With this new experimental framework, agents are now supported in the platform. According to Microsoft, agents are AI entities that specialize in being able to complete a specific task with a specific set of tools. Multiple agents can work together to complete a complex task as well.
Within Semantic Kernel, each agent can be associated with different plug-ins and functions that can help it execute its job.
The Agent Framework includes two specific agent types as well as abstractions that developers can build on. The first agent type is a Chat Completion Agent and the second is the Open AI Assistant Agent.
There are also two modes for interacting with agents: directly invoking it or by chatting with it through AgentChat.
Upcoming Agent Framework features that are being worked on right now include support for the Open AI Assistant v2, enabling serialization and restoring AgentChat, improved chat patterns, and more.
The Semantic Kernel project itself was first previewed in April 2023 and since then it has grown to 20K stars on GitHub.
Read about other recent Open-Source Projects of the Week: