Ecosystem & Stack: kubernetes

OpenHands is an AI-driven development platform that empowers users to build, run, and scale autonomous software agents for various development tasks.

An open-source AI platform offering an advanced, feature-rich chat interface compatible with all major LLMs, enabling RAG, web search, and custom agents.

A production-grade, open-source platform for building and deploying AI-powered instant messaging bots across various chat platforms.

A secure enterprise AI platform providing guardrails, a centralized MCP registry, gateway, and orchestration for managing AI usage, costs, and data security.

A user-friendly, self-hosted AI platform providing a powerful interface for interacting with various LLMs, including Ollama and OpenAI-compatible APIs, with advanced RAG capabilities.

A high-performance, cloud-native vector database designed for scalable Approximate Nearest Neighbor (ANN) search on massive unstructured data.

A dynamic service discovery, configuration, and management platform for building cloud-native applications and microservices.

A production-ready, extensible AI agent framework designed for building, deploying, and understanding intelligent agents powered by advanced LLMs, with built-in finetuning and multi-agent orchestration.

DocsGPT is an open-source AI platform for building intelligent agents and assistants, offering private, multi-model support, deep research, and document analysis for enterprise search.

A unified, open platform for accelerating AI model serving and scaling GenAI deployments with industry-leading performance across various hardware.

A distributed operating system for cloud-native application management, leveraging Kubernetes as its kernel for multi-cloud, datacenter, and edge environments.

An APM tool for large-scale distributed systems, providing real-time monitoring and code-level visibility across transactions.

LazyLLM simplifies the creation and iterative optimization of multi-agent large language model (LLM) applications with a low-code approach.

A powerful, real-time terminal UI log analysis tool offering charts, AI insights, and advanced filtering for various log streams.

An open-source GPU cluster manager that orchestrates high-performance AI inference engines like vLLM and SGLang for efficient model deployment across diverse environments.

A standardized, scalable, multi-framework platform for deploying generative and predictive AI models on Kubernetes.

An open-source, cloud-native vector database enabling semantic search at scale by combining vector similarity with structured filtering and AI capabilities.

Dynamic, resilient open-source orchestrator for building scalable and reproducible data and ML pipelines on Kubernetes.

SwanLab is an open-source, modern-design platform for tracking, visualizing, and analyzing AI/ML training experiments, supporting cloud and self-hosted deployments.

An open-source, container-native workflow engine for Kubernetes, designed to orchestrate parallel jobs and complex multi-step tasks.

An open-source platform for building, deploying, and managing end-to-end machine learning workflows on Kubernetes.

A comprehensive MLOps platform for managing, orchestrating, and scaling the machine learning lifecycle with reproducibility and automation.

A CLI tool for creating reproducible, container-based development environments, especially for AI/ML projects.

A Kubernetes-native platform for scalable distributed AI model training and LLM fine-tuning across various frameworks.

ClearML streamlines AI/ML/LLM workflows with integrated experiment tracking, data management, MLOps/LLMOps orchestration, and model serving.

Maestro is Netflix's highly scalable, general-purpose workflow orchestrator, providing a fully managed workflow-as-a-service for data and ML pipelines.

A framework for easily self-hosting and serving any open-source Large Language Models as OpenAI-compatible API endpoints in the cloud.

An MLOps and LLMOps framework for deploying, managing, and scaling AI systems, from singular models to complex data-centric applications, on Kubernetes.

An open-source, cloud-native, all-in-one MLOps platform designed for the full lifecycle management of machine learning, deep learning, and large language model development and deployment.

A low-code, declarative framework for building and deploying custom large language models (LLMs) and other deep neural networks with ease and efficiency.

A Jenkins plugin that enables dynamic provisioning and scaling of build agents as Kubernetes pods, optimizing resource utilization for CI/CD pipelines.

A secure, fast, and extensible sandbox runtime for AI agents, offering multi-language SDKs and robust container orchestration.

A portable, open-source operating system for AI agents, offering near-zero cold starts and significantly lower costs compared to traditional sandboxes, powered by WebAssembly and V8 isolates.

CrateDB is a distributed SQL database combining SQL benefits with NoSQL scalability for real-time data analysis.

A cloud-native distributed vector database for efficient similarity search of embedding vectors in AI applications.

Attu is a modern, AI-native management tool for Milvus vector databases, offering a comprehensive GUI for cluster management, data exploration, and AI-driven operations.

An all-in-one API platform for building intelligent search, recommendations, and RAG applications with advanced semantic capabilities.

A vendor-agnostic unified control plane for GPU provisioning and orchestration across clouds, Kubernetes, and on-prem for AI/ML workloads.

A multi-LoRA inference server designed to serve thousands of fine-tuned LLMs on a single GPU, significantly reducing serving costs while maintaining high throughput and low latency.

A unified open-source AI gateway and proxy for federating MCP, A2A, and REST/gRPC APIs, offering centralized governance, discovery, and observability for AI clients and agents.

A unified platform for end-to-end LLM evaluation, AI agent testing, monitoring, and optimization, designed to streamline the development and deployment of reliable AI systems.

Build low-latency, multi-modal AI agents that process real-time video and audio using various LLMs and vision models.

A high-performance data engine for AI and multimodal workloads, processing diverse data types at scale with Python and Rust.

LlamaGPT is a self-hosted, offline, and 100% private ChatGPT-like chatbot powered by Llama 2 and Code Llama, ensuring no data leaves your device.

KitOps is a CNCF open-source MLOps tool for packaging, versioning, and securely sharing AI/ML models, datasets, and code as OCI artifacts.

A high-performance, extensible API and AI Gateway for orchestrating microservices, LLM, and MCP traffic.

Orchestrates complex business processes across people, systems, and devices, offering scalable, on-demand process automation.

A cloud-native framework for building and deploying high-performance multimodal AI applications with built-in scaling and orchestration.

An open-source AI agent for investigating production incidents and finding root causes across any stack.

Apache DolphinScheduler is a modern, low-code data orchestration platform designed for agile development and high-performance management of complex data workflows and task dependencies.

An end-to-end AI platform for data, model, and pipeline orchestration, offering ETL, LLM hosting, and RAG capabilities to streamline AI application development.

An open-source developer platform for building internal tools, APIs, background jobs, and workflows, featuring a fast workflow engine and automatic UI generation from scripts.

A cloud-native, open-source search engine optimized for fast, cost-effective observability data (logs, traces, metrics) on cloud storage.

An open-source, free, self-hosted alternative to Cypress Dashboard, enabling unlimited parallel test execution and comprehensive test result management.

A free and self-hosted PaaS that simplifies application deployment on Kubernetes for developers without specialized knowledge.

Octelium is a self-hosted, open-source unified zero-trust secure access platform, offering VPN, ZTNA, API/AI gateways, PaaS, and secure tunneling capabilities for various environments.

Teleport provides secure, unified access to all infrastructure, including servers, Kubernetes, databases, and web applications, enforcing zero-trust principles.

An open-source blockchain explorer providing a comprehensive interface for inspecting and analyzing transactions, accounts, and smart contracts on EVM-compatible chains.

An open-source, real-time collaborative note-taking, wiki, and documentation platform built with Django and React, offering data ownership and self-hosting.

A graph-native platform for storing, enriching, and retrieving structured knowledge to power AI applications and intelligent agents.

A cloud-native, distributed SQL database offering horizontal scalability, high availability, and HTAP capabilities with MySQL compatibility for unpredictable workloads.

An Ingress Controller for Kubernetes that leverages NGINX and NGINX Plus to provide advanced traffic management, load balancing, and routing capabilities for containerized applications.

A Kubernetes daemon that detects and reports various node problems to the apiserver, making node health visible for improved cluster management.