[RobirdLiu]

To get started on building it yourself, you could consider a stack like: Python as the base, Ollama for local LLM serving, Whisper (e.g., via whisper.cpp) for STT, Langchain for the agent orchestration and tool integration, and something like Piper for TTS. For Notion/GCal, their official Python SDKs wrapped as Langchain tools would be the way.

This selection prioritizes a pragmatic balance between capability and a more manageable entry point for an individual project, rather than focusing strictly on the absolute SOTA or most experimental options for each component. It should provide a solid foundation for iterative development, and you can always swap out/upgrade specific parts later as you see fit

[EnthusiastShiv]

yeah this is a solid stack. kinda surprised no one's bundled this up yet into a plug-and-play AI agent starter kit. feels like the kind of thing that should already exist tbh.

[RobirdLiu]

Thank you so much for your Upvote.This is the first and only Upvote I've ever received.I thought I had answered a few HN Ask questions thoughtfully and seriously,but I ended up with 5 Downvotes.Thank you again,kind soul.I will keep working hard.I still have several great projects that I want to show to the world.In a few more months,perhaps the project I'm currently working on will meet your expectations.However,at the moment,I'm focusing on more fundamental aspects,such as exploring how to maintain continuous and meaningful cognitive activity in LLMs,as well as their ability to reflect and learn.I haven't been working on areas like tool call,memory,TTS,etc.,where there have already been significant achievements.I'll introduce it to everyone once the project is initially functional.Stay tuned!