I'd be happy to help you increase the memory limit of your agent! The best approach depends on where your agent is deployed: • Self-Hosted: You can update the

resources

section in your

agent-manifest.yaml

file to set higher memory limits. Here's an example:

spec:
  template:
    spec:
      containers:
        - name: agent-example
          image: <http://your-docker-repo.com/path-to-your-docker-build:latest|your-docker-repo.com/path-to-your-docker-build:latest>
          resources:
            requests:
              cpu: "4"
              memory: "8Gi"
            limits:
              cpu: "4"
              memory: "8Gi"

This example sets the memory limit to 8GB, but feel free to adjust it according to your workload needs. • Programmatic Monitoring: If you're managing memory through code, the

SupervisedProc

class lets you define memory limits like this:

SupervisedProc(
    memory_warn_mb=6144,    # Warn at 6GB
    memory_limit_mb=8192,   # Kill at 8GB
)

• LiveKit Cloud: The platform handles memory limits for you. If you need higher limits, you can request an increase through the project settings dashboard or reach out to sales for custom plans. Please don’t hesitate 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: kubernetes/agent-manifest.yaml | livekit-agents/livekit/agents/ipc/supervised_proc.py | Quotas and limits | LiveKit Docs | Deployment and scaling | LiveKit Docs | External data and RAG | LiveKit Docs