AI agent platform that runs locally

Question

llms are powerful now, but still feel disconnected.I want small agents that run locally (some in cloud if needed), talk to each other, read/write to notion + gcal, plan my day, and take voice input so i don&rsquo;t have to type.Just want useful automation without the bloat. Is there anything like this already? or do i need to build it?

RobirdLiu · Accepted Answer

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

karanveer · Answer

i wanted something similar, especially as im a big advocate of using time blocking method and i use gcal all the time. on top of notion and onenote.I planned to make something small around this, but currently due to limited time, i am not able to put my hands in it. If you do find a solution please do let me know as well.