3 Repos
Architecture allowing the swapping of different execution engines to support varied execution modes.
Distinct from Execution Engines: Distinct from general execution engines by focusing on the swappability/composability of the runtime itself.
Explore 3 awesome GitHub repositories matching programming languages & runtimes · Pluggable Runtimes. Refine with filters or upvote what's useful.
rkt is a pod-native container engine and runtime for Linux that executes containerized applications as isolated pods. It serves as an OCI container runtime and a Linux container manager, supporting the execution of images based on Open Container Initiative, appc, and Docker specifications. The project distinguishes itself by offering hardware-level container isolation, allowing pods to run within virtual machines using KVM or QEMU for a dedicated kernel. It further separates itself through secure container deployment practices, utilizing SELinux mandatory access control and TPM-backed integri
Employs a composable design that allows swapping different execution engines for immutable or mutable execution.
Apache Camel is an enterprise integration framework and Java integration engine designed to route and mediate data between disparate systems. It functions as a multi-runtime middleware that implements standardized enterprise integration patterns to manage how messages are routed, transformed, and processed. The framework includes a specialized gateway to connect large language models to enterprise data and internal systems using dedicated communication protocols. It utilizes a vast library of pre-built connectors to bridge different communication protocols and enable data exchange between inc
Provides a pluggable architecture allowing the routing engine to run as a standalone service or be embedded in host frameworks.
KServe is an open platform for deploying and serving generative and predictive AI models on Kubernetes. It defines inference services as custom resources with declarative YAML specifications, enabling a Kubernetes-native approach to model deployment and lifecycle management. The platform leverages Knative-based serverless scaling for automatic scale-to-zero and revision management, and supports a pluggable serving runtime architecture that maps model formats to containerized execution environments. KServe distinguishes itself through model-aware autoscaling that scales replicas based on token
Packages custom serving logic as pluggable runtimes to support proprietary or specialized model engines.