I started building muGen about four months ago and it's now stable enough for me to share.<p>muGen is a microframework for prototyping and deploying multi-modal/multi-channel (3MC) generative AI applications. Written in Python, it aims to have a simple, lean, and extensible codebase that allows developers to mix and match technologies and vendors—such as LLMs, vector storage, and communication platforms—to get from zero to deployment quickly.<p>NB: muGen currently supports AWS Bedrock, Groq, and SambaNova as completion backends so you'll need to have credentials for one of these APIs to try it. I will add support for more vendors as I get the time.