Discover community-driven integrations, libraries, and resources to extend Datadog across your stack. Filter by platform, data type, use case, and more.
The Datadog TorchServe integration enables comprehensive monitoring of your TorchServe instances by collecting metrics, events, and logs from the Inference API, Management API, and OpenMetrics endpoints. Track the overall health status, model performance, and custom metrics, and receive alerts on key events such as model additions or removals. This integration supports flexible configuration for hosts, Docker, and Kubernetes environments, helping you ensure your TorchServe deployments are performing optimally and issues are detected quickly.
Collect and graph Upbound UXP metrics, providing insights into control plane framework performance. The integration enables monitoring of Universal Crossplane and provider Kubernetes pods.
Uptime & performance monitoring made easy, providing comprehensive website monitoring and real-time alerts. The integration enables tracking of check response times and automatic event generation in Datadog.