The name is `agency`. It differs from other agent libraries, most importantly in that it's intended to address a distinct part of the overall problem, that of agent integration. It is not an agent toolchain like LangChain and others.

`agency` is a framework intended for safely integrating agents with computing systems and humans in a way that all parties can easily understand and communicate with each other.

I've spent a lot of time on the readme which contains a detailed and working walkthrough of building an agent integrated system that includes multiple types of agents, operating system integration, access control, and a flask+react based web application where users can appear as individual "agents" as well.

Also worth noting is that I _just_ pushed an update to integrate with the new functions support on the OpenAI API! (https://openai.com/blog/function-calling-and-other-api-updat...)

I'm eager to hear what people think! I developed this in order to build a foundation for some of my own ambitious ideas. If you find this useful for your own projects I'd love to know!

Thanks for checking it out! I hope this helps you build amazing things!