Awesome GitHub RepositoriesAutoscaling Systems

OpenFaaS is a serverless function platform that provides a container-native framework for deploying and managing event-driven code. It functions as an abstraction layer over container orchestrators, allowing developers to package code into scalable functions that run across Kubernetes clusters or edge computing environments. The platform distinguishes itself through a developer-centric runtime that utilizes standardized language templates and automated build pipelines to simplify the creation of container images. It features a central API gateway that manages request routing, authentication,

Deepagents is an LLM agent orchestration platform and stateful application server designed for deploying and managing AI agents built with computational graphs. It provides a containerized runtime environment that handles agent execution, state persistence, and the versioning of AI assistants. The platform distinguishes itself through deep integration with the Model Context Protocol, allowing agents to function as servers that expose tools and capabilities to external clients. It features a sophisticated observability suite for capturing execution traces, performing LLM-based evaluations agai

Neon is a serverless PostgreSQL database platform designed with a decoupled storage and compute architecture. It functions as a multi-tenant system that isolates data and compute resources for independent users on shared cloud infrastructure, utilizing a specialized PostgreSQL storage engine. The platform features a database branching system that allows for the creation of isolated, instant copies of a database for testing and development. It further distinguishes itself with an HTTP-based SQL gateway, enabling the execution of queries via HTTP requests and JSON responses without the need for

AutoMQ is a cloud-native streaming platform and Kafka-compatible message broker. It implements the Kafka protocol to provide integration with existing clients and ecosystems while functioning as a message queue that persists data directly to cloud object storage. The system decouples compute from storage, allowing processing power and storage capacity to scale independently. It utilizes a shared-log architecture and object-storage-based persistence to remove dependencies on local disks, which reduces operational costs and eliminates manual disk management. The platform includes mechanisms fo

Meshery is a service mesh management plane and cloud native infrastructure orchestrator. It provides a visual design-as-code environment for modeling microservices and infrastructure components through declarative blueprints, functioning as a centralized platform for designing, deploying, and managing service mesh infrastructure. The platform is distinguished by its ability to translate visual designs into active deployments and its use of gRPC-based adapters to integrate with diverse infrastructure providers. It features a multi-tenant architecture that manages shared workspaces and role-bas

Dynamo is a distributed inference orchestration platform designed for large language models. It functions as a system to coordinate prefill and decode phases across GPU nodes, utilizing a multi-backend runtime adapter to connect engines like vLLM and TensorRT-LLM through a unified block-oriented memory interface. An OpenAI-compatible API server provides the frontend for integration with existing tools and clients. The project is distinguished by its disaggregated serving architecture, which separates prompt processing and token generation onto independent GPU pools to optimize throughput and

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

Cluster API is a declarative framework and multi-cluster management system for automating the creation, scaling, and destruction of Kubernetes clusters across diverse infrastructures. It acts as a cluster provisioning orchestrator and infrastructure provisioner, using a centralized management cluster to operate the full lifecycle of multiple remote workload clusters. The project employs a provider-based plugin architecture that decouples core orchestration logic from specific cloud or bare-metal implementations. This allows the system to standardize the deployment of control planes, the boots

llm-d is a distributed serving framework designed for large language model inference. It functions as an inference orchestrator and gateway, providing a control plane for deploying model replicas and managing hardware accelerators. The system includes a batch inference scheduler and a cache manager to coordinate request flow and memory utilization. The project is distinguished by a disaggregated serving architecture that separates prefill and decode execution phases across specialized workers to maximize throughput. It employs a hardware-agnostic control plane and tiered cache offloading, mov