[Cloud][Newbie][Help] Hi everyone. I need a clearer, more detailed explanation of how LiveKit Cloud works. Our MVP is four Python processes per user: one real-time agent that creates the room and talks to the user, plus three data-only agents (no LLM) that join the room and guide the real-time agent. We’ve been running this locally (Windows) using

start

in separate terminals, with LiveKit’s sandbox as a basic frontend. Now we need to scale this and integrate it into an application, and I’m struggling to understand the recommended LiveKit Cloud approach and how to deploy/run these agents per user. Could someone point me in the right direction or explain the best practice?

Agents are generally per users. You run one or more of you agent processes and dispatch users and agent to a room. LiveKit cloud will loadbalance across the available agent processes you have running. It should not be much different than what you are doing on Windows except your agent process runs in the cloud now.

@refined-appointment-81829 Got it! Do you think the documentation page is sufficient for a newbie to start using LiveKit in the cloud? https://docs.livekit.io/home/cloud/ I don't know if there's a YouTube tutorial about it or a template on GitHub.

There's also docs that touch on this at https://docs.livekit.io/agents/server/lifecycle/ and https://docs.livekit.io/agents/server/agent-dispatch/. We're looking to improve our tutorial content over the coming year, so this is good feedback - I agree it's an area that would benefit from a walk-through.