Got an email from LiveKit saying the following: Y...
# ask-ai
f
Got an email from LiveKit saying the following: Your project AI_MODERATOR_SECOND_VERSION has recently reached or surpassed 5 concurrent cloud agent jobs, which is the limit set on your project. To avoid service disruption for your users, please review your options in the settings page for your project.
✅ 1
t
Thanks for reaching out, Ganesh. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
Thanks — I see you received the warning that your project AI_MODERATOR_SECOND_VERSION hit the 5 concurrent cloud agent job limit. What that means • Your project is on the Build (free) plan, which is limited to 5 concurrent agent sessions. When you hit that limit new jobs can be throttled or fail, so LiveKit sent the warning to avoid service disruption. What you can do right now • Upgrade the project plan to increase concurrency: ◦ Ship ($50/mo) → 20 concurrent sessions ◦ Scale ($500/mo) → up to 600 (starts at 50; more via dashboard) ◦ Enterprise → custom concurrency and volume pricing • Or self‑host the LiveKit Agents framework to remove LiveKit Cloud concurrency limits (requires managing your own infra). Next step I can help with • Would you like me to walk you through checking usage and upgrading the project on the LiveKit Cloud dashboard, or help evaluate self‑hosting? Sources: Pricing | LiveKit | https://livekit.com/pricing.md| | Agents on LiveKit Cloud | Deploy voice AI on global infrastructure | LiveKi..., with interactive elements
f
How do I kill these sessions in the terminal right now?
t
Thanks — I see you want to immediately kill the running agent sessions for project AI_MODERATOR_SECOND_VERSION. Short answer: there is no documented terminal command to forcibly kill individual LiveKit Cloud agent sessions. However you can end sessions now using one of these actions: • Restart the agent deployment (graceful drain): run
lk agent restart
for the agent serving that project. This stops new jobs and waits for jobs to finish (honors drain timeout). • Delete the agent deployment:
lk agent delete
— removes the agent and will stop sessions as the deployment is removed. • Delete the room via the Server API to immediately disconnect participants and end the session. Example (Python):
Copy code
await api_client.room.delete_room(api.DeleteRoomRequest(room=ctx.job.room.name))
• If you self-host agents, send SIGTERM to the agent process to trigger drain mode (not an immediate force-kill). If you’d like, tell me which option you prefer and whether you’re using LiveKit Cloud or a self-hosted agent, and I’ll give the exact
lk
commands or the API call details you need. Sources: Agents Framework | livekit/livekit_composite | DeepWiki | examples/drive-thru | livekit/livekit_composite | DeepWiki | Deployment reliability on LiveKit Cloud | LiveKit | Job lifecycle | LiveKit Documentation, with interactive elements