If I already have 1 agent deployed to cloud under the free tier and I test another by running it locally in dev mode, will the agents coincide?

Thanks for reaching out, Varun. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.

So we see an issue that running an agent locally coincides with the calling happening on the deployed agent. Why could this be happening?

I understand how this can be a bit confusing! The reason this happens is that both your locally run agent in

dev

mode and the deployed agent are connecting to the same LiveKit server instance. Since, by default, they aren’t separated by environment, both agents end up registering and responding to the same room events, which causes them to overlap in behavior. To help you avoid this, here are a few friendly suggestions: • You might try running your local

dev

agent against a separate LiveKit server instance—for example, a local server using

livekit-server --dev

. • Another approach is to use room metadata filters in your agent logic, so only one agent responds to specific events. • Also, it’s a good idea to make sure the local

dev

agent isn’t left running when you’re testing or deploying to production. Please feel free to reach out if you’d like me to walk you through any of these steps or if you have any other questions. I’m here to help! Sources: Running LiveKit locally | LiveKit Docs | README.md | Voice AI quickstart | LiveKit Docs | Voice AI quickstart | LiveKit Docs | README.md