{ "schemaVersion": "1.4", "name": "ARuntime Content Catalog", "description": "Canonical route, audience, search-intent, review, relationship, and content-integrity metadata for ARuntime.com. Machine-readable records mirror visible public pages and do not add private authority.", "version": "3.9.0", "updatedUtc": "2026-06-27T02:30:00Z", "canonicalBase": "https://aruntime.com/", "taxonomyNotice": "The ARuntime layer model is an editorial framework, not a formal standard.", "itemCount": 84, "items": [ { "id": "home", "title": "Home", "url": "https://aruntime.com/", "summary": "ARuntime.com explains artificial intelligence runtimes across the full execution stack.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Readers new to AI runtimes; platform architects; technical decision-makers", "level": "Start Here", "searchIntent": "AI runtime definition and stack orientation", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "start-here", "title": "Start Here", "url": "https://aruntime.com/start-here/", "summary": "Start with definitions, the layered runtime stack, execution paths, use cases, and a glossary.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Readers new to AI runtimes and role-based learners", "level": "Start Here", "searchIntent": "Orient readers to the AI runtime stack", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "overview", "title": "AI Runtime Overview", "url": "https://aruntime.com/overview/", "summary": "A vendor-neutral overview of AI runtime layers, from compilers and inference engines to model serving, deployment, agentic execution, security, and governance.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Readers who need a precise definition; architects; engineering leaders", "level": "Start Here", "searchIntent": "Define AI runtime and distinguish its layers", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "start-here", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "taxonomy", "title": "AI Runtime Taxonomy", "url": "https://aruntime.com/taxonomy/", "summary": "A vendor-neutral taxonomy of AI runtime layers, categories, execution models, deployment boundaries, hardware targets, and system responsibilities.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Platform architects; ML systems engineers; technical analysts", "level": "Start Here", "searchIntent": "Classify AI runtime categories and boundaries", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "start-here", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "how-ai-runtimes-work", "title": "How AI Runtimes Work", "url": "https://aruntime.com/how-ai-runtimes-work/", "summary": "How model artifacts become executable programs and how production requests move through scheduling, inference, tools, policy, telemetry, memory, and failure handling.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "Infrastructure engineers; application developers; technical decision-makers", "level": "Start Here", "searchIntent": "Explain model and request execution paths", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "start-here", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "runtime-stack-diagram", "title": "Runtime Stack Diagram", "url": "https://aruntime.com/runtime-stack-diagram/", "summary": "An accessible diagram and text description of the seven-layer AI runtime stack.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "All readers", "level": "Start Here", "searchIntent": "View an accessible AI runtime stack diagram", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "start-here", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "glossary", "title": "AI Runtime Glossary", "url": "https://aruntime.com/glossary/", "summary": "Definitions for the complete AI runtime stack, generated from the reviewed version-controlled glossary catalog.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Readers learning AI runtime concepts; technical decision-makers", "level": "Foundations", "searchIntent": "A searchable glossary of AI runtime terminology across compilers, inference engines, serving systems, edge/browser runtimes, agentic runtimes, security, and observability.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "start-here", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "runtime-stack", "title": "Runtime Stack", "url": "https://aruntime.com/runtime-stack/", "summary": "Navigate hardware, kernels, compilers, inference engines, serving, agentic runtimes, and product workflows.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Platform architects; AI infrastructure engineers; ML systems engineers", "level": "Runtime Stack", "searchIntent": "Navigate the seven AI runtime layers", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "hardware-system-substrate", "title": "Hardware and System Substrate", "url": "https://aruntime.com/hardware-system-substrate/", "summary": "Hardware, memory, drivers, interconnects, isolation, topology, power, and system constraints beneath AI runtimes.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "Infrastructure and ML systems engineers", "level": "Runtime Stack", "searchIntent": "Explain hardware substrate responsibilities in AI runtime architecture", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "kernels-hardware-libraries", "title": "Kernels and Hardware Libraries", "url": "https://aruntime.com/kernels-hardware-libraries/", "summary": "Tensor kernels, device libraries, collectives, communication paths, and low-level performance boundaries.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "ML systems engineers; compiler and performance engineers", "level": "Runtime Stack", "searchIntent": "Explain AI kernel and hardware-library runtime responsibilities", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "execution-models", "title": "Execution Models", "url": "https://aruntime.com/execution-models/", "summary": "Compare eager, graph, JIT, AOT, interpreted, dataflow, and hybrid AI execution models, including dynamic shapes, guards, warmup, caches, fallback, and deployment trade-offs.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Readers learning AI runtime concepts; technical decision-makers", "level": "Runtime Stack", "searchIntent": "Compare eager, graph, JIT, AOT, interpreted, dataflow, and hybrid AI execution models, including dynamic shapes, guards, warmup, caches, fallback, and deployment trade-offs.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "hardware-targets", "title": "Hardware Targets", "url": "https://aruntime.com/hardware-targets/", "summary": "Understand CPU, GPU, TPU, NPU, FPGA, browser, mobile, and heterogeneous AI hardware targets through memory bandwidth, precision, interconnect, power, and runtime constraints.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Readers learning AI runtime concepts; technical decision-makers", "level": "Runtime Stack", "searchIntent": "Understand CPU, GPU, TPU, NPU, FPGA, browser, mobile, and heterogeneous AI hardware targets through memory bandwidth, precision, interconnect, power, and runtime constraints.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "model-formats-and-irs", "title": "Model Formats and Intermediate Representations", "url": "https://aruntime.com/model-formats-and-irs/", "summary": "Compare ONNX, StableHLO, MLIR dialects, exported PyTorch programs, GGUF, TensorRT engines, ExecuTorch PTE files, and auxiliary model assets by role and runtime implications.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Readers learning AI runtime concepts; technical decision-makers", "level": "Runtime Stack", "searchIntent": "Compare ONNX, StableHLO, MLIR dialects, exported PyTorch programs, GGUF, TensorRT engines, ExecuTorch PTE files, and auxiliary model assets by role and runtime implications.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "compiler-pipeline", "title": "Compiler and Graph Runtimes", "url": "https://aruntime.com/compiler-pipeline/", "summary": "A practical AI compiler pipeline guide covering graph capture, intermediate representations, optimization, partitioning, lowering, code generation, memory planning, AOT/JIT, fallback, and warmup.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "ML systems engineers; AI infrastructure engineers", "level": "Runtime Stack", "searchIntent": "A practical AI compiler pipeline guide covering graph capture, intermediate representations, optimization, partitioning, lowering, code generation, memory planning, AOT/JIT, fallback, and warmup.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "optimization-techniques", "title": "Optimization Techniques", "url": "https://aruntime.com/optimization-techniques/", "summary": "A practical guide to graph rewrites, fusion, tiling, memory planning, FlashAttention-style kernels, quantization, sparsity, batching, caching, speculation, and autotuning.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "ML systems engineers; AI infrastructure engineers", "level": "Runtime Stack", "searchIntent": "A practical guide to graph rewrites, fusion, tiling, memory planning, FlashAttention-style kernels, quantization, sparsity, batching, caching, speculation, and autotuning.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "llm-inference", "title": "Model and LLM Inference", "url": "https://aruntime.com/llm-inference/", "summary": "Understand LLM inference mechanics, including prefill, decode, KV cache, continuous batching, prefix reuse, quantization, structured generation, cancellation, tail latency, and production metrics.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "ML systems engineers; AI infrastructure engineers", "level": "Runtime Stack", "searchIntent": "Understand LLM inference mechanics, including prefill, decode, KV cache, continuous batching, prefix reuse, quantization, structured generation, cancellation, tail latency, and production metrics.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "kv-cache-memory", "title": "KV Cache and Runtime Memory", "url": "https://aruntime.com/kv-cache-memory/", "summary": "A deep guide to KV-cache architecture, PagedAttention, prefix caching, RadixAttention, tiered offload, cache-aware routing, isolation, memory sizing, and observability.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "ML systems engineers; AI infrastructure engineers", "level": "Runtime Stack", "searchIntent": "A deep guide to KV-cache architecture, PagedAttention, prefix caching, RadixAttention, tiered offload, cache-aware routing, isolation, memory sizing, and observability.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "scheduling-and-batching", "title": "Scheduling and Batching", "url": "https://aruntime.com/scheduling-and-batching/", "summary": "Guide to AI inference scheduling and batching: admission control, continuous batching, dynamic batching, chunked prefill, fairness, priorities, backpressure, cancellation, and Goodput.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "ML systems engineers; AI infrastructure engineers", "level": "Runtime Stack", "searchIntent": "Guide to AI inference scheduling and batching: admission control, continuous batching, dynamic batching, chunked prefill, fairness, priorities, backpressure, cancellation, and Goodput.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "speculative-decoding", "title": "Speculative Decoding", "url": "https://aruntime.com/speculative-decoding/", "summary": "Learn speculative decoding mechanics, draft and target models, verification, acceptance rate, EAGLE, Medusa, multi-token prediction, integration constraints, metrics, and failure modes.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "ML systems engineers; AI infrastructure engineers", "level": "Runtime Stack", "searchIntent": "Learn speculative decoding mechanics, draft and target models, verification, acceptance rate, EAGLE, Medusa, multi-token prediction, integration constraints, metrics, and failure modes.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "model-serving-orchestration", "title": "Model Serving", "url": "https://aruntime.com/model-serving-orchestration/", "summary": "A practical guide to model servers and serving platforms: APIs, repositories, loading, readiness, batching, multi-model hosting, autoscaling, canaries, rollback, backpressure, and observability.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "Platform architects; infrastructure engineers", "level": "Runtime Stack", "searchIntent": "A practical guide to model servers and serving platforms: APIs, repositories, loading, readiness, batching, multi-model hosting, autoscaling, canaries, rollback, backpressure, and observability.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "distributed-inference", "title": "Distributed Inference", "url": "https://aruntime.com/distributed-inference/", "summary": "Guide to tensor, pipeline, data, expert, context, sequence, and disaggregated prefill/decode inference, including interconnects, KV transfer, locality, scheduling, and failure handling.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "Platform architects; infrastructure engineers", "level": "Runtime Stack", "searchIntent": "Guide to tensor, pipeline, data, expert, context, sequence, and disaggregated prefill/decode inference, including interconnects, KV transfer, locality, scheduling, and failure handling.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "edge-browser-runtimes", "title": "Edge and Browser Runtimes", "url": "https://aruntime.com/edge-browser-runtimes/", "summary": "Local, browser, mobile, NPU, offline, constrained, and privacy-preserving AI runtime deployment.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "Browser, mobile, edge, and privacy-focused developers", "level": "Runtime Stack", "searchIntent": "Compare edge and browser AI runtime boundaries", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "browser-runtimes", "title": "Browser Runtimes", "url": "https://aruntime.com/browser-runtimes/", "summary": "Build browser AI runtimes with WebAssembly, WebGPU, WebNN, ONNX Runtime Web, Workers, model caching, I/O binding, graph capture, progressive enhancement, privacy, and fallback.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Infrastructure engineers; developers selecting deployment targets", "level": "Runtime Stack", "searchIntent": "Build browser AI runtimes with WebAssembly, WebGPU, WebNN, ONNX Runtime Web, Workers, model caching, I/O binding, graph capture, progressive enhancement, privacy, and fallback.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "edge-mobile-tinyml", "title": "Edge, Mobile, and TinyML", "url": "https://aruntime.com/edge-mobile-tinyml/", "summary": "Design edge, mobile, and TinyML runtimes with AOT artifacts, ExecuTorch, delegates, quantization, CPU/GPU/NPU partitioning, offline operation, fleet updates, and real-time constraints.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Infrastructure engineers; developers selecting deployment targets", "level": "Runtime Stack", "searchIntent": "Design edge, mobile, and TinyML runtimes with AOT artifacts, ExecuTorch, delegates, quantization, CPU/GPU/NPU partitioning, offline operation, fleet updates, and real-time constraints.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "local-desktop", "title": "Local Desktop Runtimes", "url": "https://aruntime.com/local-desktop/", "summary": "Guide to local AI runtimes on desktops and workstations, including quantized packages, CPU/GPU offload, local model servers, memory mapping, privacy, updates, and benchmarking.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Infrastructure engineers; developers selecting deployment targets", "level": "Runtime Stack", "searchIntent": "Guide to local AI runtimes on desktops and workstations, including quantized packages, CPU/GPU offload, local model servers, memory mapping, privacy, updates, and benchmarking.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "agentic-runtimes", "title": "Agentic and Application Runtimes", "url": "https://aruntime.com/agentic-runtimes/", "summary": "A production guide to agentic runtimes: identity, context, MCP tools and resources, typed execution, memory scopes, durable workflows, human approval, policy, replay, evaluation, and failure containment.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Agent developers; platform architects; governance leaders", "level": "Runtime Stack", "searchIntent": "Define the agentic application-runtime layer", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "product-workflow-layer", "title": "Product and Workflow Layer", "url": "https://aruntime.com/product-workflow-layer/", "summary": "User experience, domain records, business workflow, product state, and outcomes above runtime execution.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "Application architects; product engineers; technical product leaders", "level": "Runtime Stack", "searchIntent": "Explain the product layer above AI runtimes", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtime-stack", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "build-operate", "title": "Build and Operate", "url": "https://aruntime.com/build-operate/", "summary": "Design runtime planes, deployment topologies, security, observability, evaluation, capacity, and recovery.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Platform architects; operators; security and governance leaders", "level": "Build and Operate", "searchIntent": "Design and operate production AI runtime architecture", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "reference-architecture", "title": "Reference Architecture", "url": "https://aruntime.com/reference-architecture/", "summary": "Detailed AI runtime reference architecture with request gateway, identity, context providers, model router, inference adapters, tool broker, memory, policy, workflow, evaluation, telemetry, and deployment variants.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Platform architects; implementation teams; security and governance leaders", "level": "Build and Operate", "searchIntent": "Provide a concrete AI runtime implementation blueprint", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "runtime-architecture", "title": "Runtime Architecture", "url": "https://aruntime.com/runtime-architecture/", "summary": "A four-plane AI runtime reference architecture covering control, context, execution, trust, component contracts, deployment topologies, failure domains, and portability.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "Platform architects; infrastructure engineers; security architects", "level": "Build and Operate", "searchIntent": "Explain AI runtime architecture concepts and boundaries", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "control-execution-planes", "title": "Control and Execution Planes", "url": "https://aruntime.com/control-execution-planes/", "summary": "Control, execution, data, and evidence-plane ownership, data flow, trust boundaries, and degraded behavior.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "Platform architects; operators; security engineers", "level": "Build and Operate", "searchIntent": "Separate AI runtime control and execution planes", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "deployment-patterns", "title": "Deployment Patterns", "url": "https://aruntime.com/deployment-patterns/", "summary": "Compare browser, local, mobile, edge, private-cloud, managed-cloud, Kubernetes, serverless, hybrid, air-gapped, and benchmark AI runtime deployment patterns.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Infrastructure engineers; developers selecting deployment targets", "level": "Build and Operate", "searchIntent": "Compare browser, local, mobile, edge, private-cloud, managed-cloud, Kubernetes, serverless, hybrid, air-gapped, and benchmark AI runtime deployment patterns.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "cloud-data-center", "title": "Cloud and Data Center Runtimes", "url": "https://aruntime.com/cloud-data-center/", "summary": "Design cloud and private data-center AI runtimes across GPU clusters, Kubernetes, managed platforms, autoscaling, networking, tenancy, resilience, and cost.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Infrastructure engineers; developers selecting deployment targets", "level": "Build and Operate", "searchIntent": "Design cloud and private data-center AI runtimes across GPU clusters, Kubernetes, managed platforms, autoscaling, networking, tenancy, resilience, and cost.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "serverless-runtime", "title": "Serverless AI Runtime Patterns", "url": "https://aruntime.com/serverless-runtime/", "summary": "Design serverless and microVM AI runtime patterns with cold-start budgets, model packaging, warm pools, scale-to-zero, burst admission, storage, observability, and side-effect safety.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Infrastructure engineers; developers selecting deployment targets", "level": "Build and Operate", "searchIntent": "Design serverless and microVM AI runtime patterns with cold-start budgets, model packaging, warm pools, scale-to-zero, burst admission, storage, observability, and side-effect safety.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "hybrid-runtime", "title": "Hybrid AI Runtime Design", "url": "https://aruntime.com/hybrid-runtime/", "summary": "Design local-edge-cloud hybrid AI runtimes with policy routing, fallback, state reconciliation, model parity, cache boundaries, observability, and data residency.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Infrastructure engineers; developers selecting deployment targets", "level": "Build and Operate", "searchIntent": "Design local-edge-cloud hybrid AI runtimes with policy routing, fallback, state reconciliation, model parity, cache boundaries, observability, and data residency.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "security-governance", "title": "Security and Governance", "url": "https://aruntime.com/security-governance/", "summary": "AI runtime security and governance guide covering prompt injection, tool authorization, data exfiltration, model supply chain, sandboxing, memory poisoning, multi-tenancy, audit, approval, and incident response.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Platform operators; security and governance leaders; engineering managers", "level": "Build and Operate", "searchIntent": "AI runtime security and governance guide covering prompt injection, tool authorization, data exfiltration, model supply chain, sandboxing, memory poisoning, multi-tenancy, audit, approval, and incident response.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "runtime-observability", "title": "Runtime Observability", "url": "https://aruntime.com/runtime-observability/", "summary": "Practical AI runtime observability covering traces, metrics, logs, token timing, cache metrics, tool and policy events, cost attribution, evaluation, replay, profiling, and privacy.", "contentType": "Reference page", "contentStatus": "Architecture", "audience": "Platform architects; infrastructure engineers", "level": "Build and Operate", "searchIntent": "Practical AI runtime observability covering traces, metrics, logs, token timing, cache metrics, tool and policy events, cost attribution, evaluation, replay, profiling, and privacy.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "evaluation", "title": "Evaluation", "url": "https://aruntime.com/evaluation/", "summary": "Versioned offline and online evaluation for model behavior, runtime controls, tool use, policy, and business outcomes.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "ML engineers; platform teams; product and governance leaders", "level": "Build and Operate", "searchIntent": "Evaluate AI runtime quality, safety, policy, and outcomes", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "benchmarking", "title": "Benchmarking AI Runtimes", "url": "https://aruntime.com/benchmarking/", "summary": "Benchmark AI runtimes correctly with TTFT, TPOT, ITL, Goodput, throughput, tail latency, quality, concurrency, cache state, hardware, methodology, cost, power, and reproducibility.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Platform operators; security and governance leaders; engineering managers", "level": "Build and Operate", "searchIntent": "Benchmark AI runtimes correctly with TTFT, TPOT, ITL, Goodput, throughput, tail latency, quality, concurrency, cache state, hardware, methodology, cost, power, and reproducibility.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "cost-capacity-planning", "title": "Cost and Capacity Planning", "url": "https://aruntime.com/cost-capacity-planning/", "summary": "Plan AI runtime capacity and cost using model memory, KV cache, concurrency, Goodput, arrival rates, queueing, accelerator utilization, warm pools, provider cost, and task outcomes.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Platform operators; security and governance leaders; engineering managers", "level": "Build and Operate", "searchIntent": "Plan AI runtime capacity and cost using model memory, KV cache, concurrency, Goodput, arrival rates, queueing, accelerator utilization, warm pools, provider cost, and task outcomes.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "runtime-selection-guide", "title": "Runtime Selection Guide", "url": "https://aruntime.com/runtime-selection-guide/", "summary": "Choose an AI runtime using model format, latency, throughput, context, hardware, deployment, privacy, tools, durability, observability, licensing, maturity, and operational capability.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Platform operators; security and governance leaders; engineering managers", "level": "Build and Operate", "searchIntent": "Choose an AI runtime using model format, latency, throughput, context, hardware, deployment, privacy, tools, durability, observability, licensing, maturity, and operational capability.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "failure-recovery", "title": "Failure Recovery", "url": "https://aruntime.com/failure-recovery/", "summary": "Detection, retry eligibility, idempotency, rollback, compensation, escalation, and evidence for runtime failures.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Platform engineers; application developers; incident responders", "level": "Build and Operate", "searchIntent": "Design AI runtime failure detection and recovery", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "build-operate", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "developers", "title": "Developers", "url": "https://aruntime.com/developers/", "summary": "Implement versioned request, tool, policy, evidence, and trace contracts with runnable examples.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Application developers; platform engineers; API and security engineers", "level": "Developers", "searchIntent": "Implement AI runtime contracts and governed execution", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "developer-guide", "title": "Developer Guide", "url": "https://aruntime.com/developer-guide/", "summary": "Build production AI runtimes with versioned request/response contracts, adapters, typed tools, routing, memory, policy checkpoints, traces, idempotency, streaming, evaluations, and SLOs.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Application developers; platform engineers", "level": "Developers", "searchIntent": "Build production AI runtimes with versioned request/response contracts, adapters, typed tools, routing, memory, policy checkpoints, traces, idempotency, streaming, evaluations, and SLOs.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "developers", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "runtime-contract", "title": "Legacy Runtime Contract", "url": "https://aruntime.com/runtime-contract/", "summary": "Retired in favor of the versioned Runtime Request Contract.", "contentType": "Reference page", "contentStatus": "Retired", "audience": "Application developers; platform engineers; API designers", "level": "Developers", "searchIntent": "Legacy alias redirected to the canonical Runtime Request Contract.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "developers", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "runtime-request-contract", "title": "Runtime Request Contract", "url": "https://aruntime.com/runtime-request-contract/", "summary": "A readable specification and JSON Schema for identity, tenancy, risk, permissions, route constraints, tools, memory, budgets, approvals, output, traces, and retention.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Application developers; platform and API engineers", "level": "Developers", "searchIntent": "Specify a versioned AI runtime request envelope", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "developers", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "tool-contract", "title": "Tool Contract", "url": "https://aruntime.com/tool-contract/", "summary": "Tool identity, schemas, authentication, permissions, side effects, egress, timeout, retry, idempotency, approval, compensation, audit, and deprecation.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Agent developers; platform engineers; security engineers", "level": "Developers", "searchIntent": "Specify typed and governed AI tool execution", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "developers", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "policy-approval-contract", "title": "Policy and Approval Contract", "url": "https://aruntime.com/policy-approval-contract/", "summary": "Versioned policy decisions, reason codes, approval authority, expiration, override rules, evidence, redaction, and review paths.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Security engineers; governance leaders; runtime developers", "level": "Developers", "searchIntent": "Specify policy decisions and approval gates for AI execution", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "developers", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "evidence-schema", "title": "Evidence Schema", "url": "https://aruntime.com/evidence-schema/", "summary": "A minimized evidence record for request identity, versions, context references, decisions, tool effects, failures, retries, recovery, evaluation, redaction, and retention.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Platform engineers; auditors; governance and incident teams", "level": "Developers", "searchIntent": "Record minimized, correlated AI runtime evidence", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "developers", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "trace-schema", "title": "Trace Schema", "url": "https://aruntime.com/trace-schema/", "summary": "A trace envelope that separates infrastructure, model, tool, policy, business-outcome, and evaluation telemetry.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Platform engineers; SRE; observability and evaluation teams", "level": "Developers", "searchIntent": "Correlate infrastructure, model, tool, policy, outcome, and evaluation traces", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "developers", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "examples", "title": "AI Runtime Examples", "url": "https://aruntime.com/examples/", "summary": "Complete AI runtime architecture examples for local assistants, enterprise RAG, browser inference, mobile vision, high-throughput LLM serving, durable agents, and hybrid routing.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Application developers; platform engineers", "level": "Developers", "searchIntent": "Complete AI runtime architecture examples for local assistants, enterprise RAG, browser inference, mobile vision, high-throughput LLM serving, durable agents, and hybrid routing.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "developers", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "integration-checklists", "title": "Integration Checklists", "url": "https://aruntime.com/integration-checklists/", "summary": "Production AI runtime integration checklists for contracts, model adapters, tools, context/RAG, memory, security, observability, benchmarking, deployment, and operations.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Application developers; platform engineers", "level": "Developers", "searchIntent": "Production AI runtime integration checklists for contracts, model adapters, tools, context/RAG, memory, security, observability, benchmarking, deployment, and operations.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "developers", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "runtimes", "title": "Runtime Directory", "url": "https://aruntime.com/runtimes/", "summary": "Browse a vendor-neutral AI runtime directory covering compiler and graph runtimes, inference engines, model servers, serving platforms, edge, browser, and local runtime systems.", "contentType": "Reference page", "contentStatus": "Research", "audience": "Architects and developers evaluating runtime products", "level": "Directory", "searchIntent": "Browse structured AI runtime profiles", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "compare", "title": "Compare Runtime Categories", "url": "https://aruntime.com/compare/", "summary": "Compare AI runtimes responsibly by category, stack layer, model, hardware, precision, workload, SLO, quality, feature boundary, operations, licensing, and evidence.", "contentType": "Reference page", "contentStatus": "Research", "audience": "Technical evaluators; procurement teams; platform architects", "level": "Directory", "searchIntent": "Compare AI runtime categories within an explicit scope", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtimes", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "product-comparison-scope", "title": "Product Comparison Scope", "url": "https://aruntime.com/product-comparison-scope/", "summary": "Required scope, versions, hardware, workloads, exclusions, verification dates, and unverified fields for runtime comparisons.", "contentType": "Reference page", "contentStatus": "Research", "audience": "Technical evaluators and procurement teams", "level": "Directory", "searchIntent": "Define safeguards for AI runtime product comparisons", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtimes", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "directory-methodology", "title": "Directory Methodology", "url": "https://aruntime.com/directory-methodology/", "summary": "How runtime directory entries are sourced, categorized, versioned, reviewed, corrected, and marked when information is unverified.", "contentType": "Reference page", "contentStatus": "Research", "audience": "Vendors; maintainers; evaluators; readers", "level": "Directory", "searchIntent": "Explain runtime directory inclusion, categorization, and verification", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "runtimes", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "research", "title": "Research", "url": "https://aruntime.com/research/", "summary": "Review reports, protocols, source records, methodology, policy, corrections, and the changelog.", "contentType": "Reference page", "contentStatus": "Research", "audience": "Researchers; technical analysts; vendors; maintainers; readers", "level": "Research", "searchIntent": "Navigate ARuntime research, sources, and editorial methods", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "reports", "title": "Reports", "url": "https://aruntime.com/reports/", "summary": "Versioned reports on AI runtime architecture, execution models, deployment, governance, and ecosystem changes.", "contentType": "Reference page", "contentStatus": "Research", "audience": "Researchers; architects; technical analysts", "level": "Research", "searchIntent": "Browse long-form AI runtime reports", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "protocols-ecosystem", "title": "Protocols and Ecosystem", "url": "https://aruntime.com/protocols-ecosystem/", "summary": "Protocols and specifications for model formats, serving APIs, tools, identity, telemetry, policy, and evidence.", "contentType": "Reference page", "contentStatus": "Research", "audience": "Platform architects; protocol implementers; analysts", "level": "Research", "searchIntent": "Map protocols that affect AI runtime interoperability", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "industry-landscape", "title": "Industry Landscape", "url": "https://aruntime.com/industry-landscape/", "summary": "A responsibility-based landscape across compilers, inference engines, serving, distributed execution, edge, browser, and agentic application runtimes.", "contentType": "Reference page", "contentStatus": "Research", "audience": "Technical decision-makers; analysts; engineering managers", "level": "Research", "searchIntent": "Understand the AI runtime ecosystem by responsibility", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "resources", "title": "AI Runtime Resources", "url": "https://aruntime.com/resources/", "summary": "A curated resource hub for ARuntime.com reference pages, implementation guides, runtime directory entries, and trust resources.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Technical readers", "level": "Research", "searchIntent": "A curated resource hub for ARuntime.com reference pages, implementation guides, runtime directory entries, and trust resources.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "future-trends", "title": "Future Trends in AI Runtimes", "url": "https://aruntime.com/future-trends/", "summary": "Evidence-based AI runtime trends: speculative decoding, disaggregated serving, cache-aware routing, AI PCs, WebNN, dynamic precision, energy-aware scheduling, confidential execution, and agent runtime infrastructure.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Platform operators; security and governance leaders; engineering managers", "level": "Research", "searchIntent": "Evidence-based AI runtime trends: speculative decoding, disaggregated serving, cache-aware routing, AI PCs, WebNN, dynamic precision, energy-aware scheduling, confidential execution, and agent runtime infrastructure.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "research-methodology", "title": "Research Methodology", "url": "https://aruntime.com/research-methodology/", "summary": "ARuntime.com research methodology covering source discovery, primary-source verification, claim matrix, benchmark review, terminology, diagrams, code validation, freshness, and correction workflow.", "contentType": "Reference page", "contentStatus": "Research", "audience": "Technical analysts; vendors; contributors", "level": "Research", "searchIntent": "Explain research, source selection, and product verification", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "editorial-policy", "title": "Editorial Policy", "url": "https://aruntime.com/editorial-policy/", "summary": "ARuntime.com editorial policy for technical accuracy, vendor neutrality, source hierarchy, benchmark claims, time-sensitive facts, AI assistance, conflicts, corrections, and review dates.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Readers, vendors, contributors, and reviewers", "level": "Research", "searchIntent": "Explain editorial standards and corrections", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "corrections", "title": "Corrections", "url": "https://aruntime.com/corrections/", "summary": "Report corrections to ARuntime.com and review the process for verification, material corrections, source updates, security-sensitive reports, and publication records.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Readers, vendors, maintainers, and contributors", "level": "Research", "searchIntent": "Submit and review factual corrections", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "ai-ready-web", "title": "Content Quality and Discovery for ARuntime.com", "url": "https://aruntime.com/ai-ready-web/", "summary": "Public record of how ARuntime.com keeps runtime pages visible, source-grounded, accessible, discoverable, and bounded without copied guidance or hidden bot text.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Readers, maintainers, search crawlers, answer systems, and reviewers validating ARuntime public content quality", "level": "Research and Trust", "searchIntent": "ARuntime content quality discovery files machine readable runtime pages boundaries", "lastReviewedUtc": "2026-06-27", "lastMaterialChangeUtc": "2026-06-27", "parent": "", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "answer-engine-optimization", "title": "Answer-Ready Runtime Definitions", "url": "https://aruntime.com/ai-ready-web/answer-engine-optimization/", "summary": "How ARuntime.com structures its own runtime definitions and comparisons so answers remain concise, visible, citable, and bounded.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Editors, architects, and reviewers checking whether ARuntime runtime definitions can be summarized accurately", "level": "Research and Trust", "searchIntent": "ARuntime answer ready runtime definitions direct answer canonical page", "lastReviewedUtc": "2026-06-27", "lastMaterialChangeUtc": "2026-06-27", "parent": "ai-ready-web", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "generative-engine-optimization", "title": "Generative Citation Support for Runtime Content", "url": "https://aruntime.com/ai-ready-web/generative-engine-optimization/", "summary": "How ARuntime.com keeps runtime content retrievable, comparable, citable, and bounded for generative summaries without hidden prompts or copied guidance.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Maintainers, researchers, and reviewers checking generated summaries against ARuntime source pages", "level": "Research and Trust", "searchIntent": "ARuntime generative citation support runtime content route inventory llms", "lastReviewedUtc": "2026-06-27", "lastMaterialChangeUtc": "2026-06-27", "parent": "ai-ready-web", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "seo", "title": "Search Discovery for AI Runtime Pages", "url": "https://aruntime.com/ai-ready-web/seo/", "summary": "Search-discovery implementation record for ARuntime.com titles, descriptions, canonical URLs, internal links, sitemap, robots, feeds, and visible structured data.", "contentType": "Reference page", "contentStatus": "Production guidance", "audience": "Site maintainers and technical reviewers auditing ARuntime search metadata and discovery files", "level": "Research and Trust", "searchIntent": "ARuntime search discovery metadata sitemap robots structured data runtime pages", "lastReviewedUtc": "2026-06-27", "lastMaterialChangeUtc": "2026-06-27", "parent": "ai-ready-web", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "changelog", "title": "Changelog", "url": "https://aruntime.com/changelog/", "summary": "Material site, taxonomy, source, methodology, and correction changes with UTC dates.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Readers, contributors, and maintainers", "level": "Research", "searchIntent": "Review material site and taxonomy changes", "lastReviewedUtc": "2026-06-27", "lastMaterialChangeUtc": "2026-06-27", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "about", "title": "About ARuntime.com", "url": "https://aruntime.com/about/", "summary": "About ARuntime.com, its mission, layered AI runtime taxonomy, audience, editorial standards, Michael Kappel, and publication approach.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "All readers", "level": "Utility", "searchIntent": "Explain site purpose and taxonomy ownership", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "contact", "title": "Contact", "url": "https://aruntime.com/contact/", "summary": "Contact Michael Kappel for AI runtime architecture, enterprise software modernization, technical collaboration, source recommendations, and ARuntime.com feedback.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "Readers and professional contacts", "level": "Utility", "searchIntent": "Contact the site editor", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "accessibility", "title": "Accessibility", "url": "https://aruntime.com/accessibility/", "summary": "Accessibility features, current conformance target, known limits, and issue-reporting route.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "All visitors", "level": "Utility", "searchIntent": "Explain accessibility support and issue reporting", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "privacy", "title": "Privacy Policy", "url": "https://aruntime.com/privacy/", "summary": "Privacy baseline for the ARuntime.com theme package and live-site considerations for production WordPress deployment.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "All visitors", "level": "Legal", "searchIntent": "Explain site privacy practices", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "terms", "title": "Terms of Use", "url": "https://aruntime.com/terms/", "summary": "Terms of use for ARuntime.com as a public technical reference site.", "contentType": "Reference page", "contentStatus": "Foundational", "audience": "All visitors", "level": "Legal", "searchIntent": "Explain site terms of use", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "links", "title": "Site Links and Navigation", "url": "https://aruntime.com/links/", "summary": "Retired link hub. Requests redirect to the Start Here index.", "contentType": "Reference page", "contentStatus": "Retired", "audience": "Readers, contributors, and vendors", "level": "Trust", "searchIntent": "Legacy link hub redirected to Start Here.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "noindex" }, { "id": "support", "title": "Support and Corrections", "url": "https://aruntime.com/support/", "summary": "Retired support page. Requests redirect to the corrections workflow.", "contentType": "Reference page", "contentStatus": "Retired", "audience": "Readers, contributors, and vendors", "level": "Trust", "searchIntent": "Legacy support page redirected to the canonical corrections workflow.", "lastReviewedUtc": "2026-06-23", "lastMaterialChangeUtc": "2026-06-23", "parent": "research", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "noindex" }, { "id": "runtime-types", "title": "Emerging AI Runtime Types", "url": "https://aruntime.com/runtime-types/", "summary": "A boundary-focused map of emerging AI runtime categories including AIR, AEE, MIR, SRE, CRE, and NEE.", "contentType": "Reference page", "contentStatus": "Emerging proposal", "audience": "Architects, AI platform engineers, technical decision makers", "level": "Architecture", "searchIntent": "emerging AI runtime types AIR AEE MIR SRE CRE NEE", "lastReviewedUtc": "2026-06-27", "lastMaterialChangeUtc": "2026-06-27", "parent": "runtime-stack-diagram", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "autonomous-inference-runtime", "title": "Autonomous Inference Runtime", "url": "https://aruntime.com/runtime-types/autonomous-inference-runtime/", "summary": "Local or edge inference runtime for fast, private, resilient, power-aware operation near devices, sensors, users, robots, vehicles, and industrial processes.", "contentType": "Reference page", "contentStatus": "Emerging proposal", "audience": "AI architects, platform engineers, runtime implementers", "level": "Architecture", "searchIntent": "Autonomous Inference Runtime definition architecture runtime", "lastReviewedUtc": "2026-06-27", "lastMaterialChangeUtc": "2026-06-27", "parent": "runtime-types", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "agentic-execution-environment", "title": "Agentic Execution Environment", "url": "https://aruntime.com/runtime-types/agentic-execution-environment/", "summary": "Sandboxed execution boundary for autonomous or semi-autonomous agents that can call tools, run code, write files, and trigger side effects.", "contentType": "Reference page", "contentStatus": "Emerging proposal", "audience": "AI architects, platform engineers, runtime implementers", "level": "Architecture", "searchIntent": "Agentic Execution Environment definition architecture runtime", "lastReviewedUtc": "2026-06-27", "lastMaterialChangeUtc": "2026-06-27", "parent": "runtime-types", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "machine-intelligence-runtime", "title": "Machine Intelligence Runtime", "url": "https://aruntime.com/runtime-types/machine-intelligence-runtime/", "summary": "Enterprise runtime control layer for model-backed work across identity, policy, memory, tools, routing, telemetry, audit, budgets, and governed state changes.", "contentType": "Reference page", "contentStatus": "Emerging proposal", "audience": "AI architects, platform engineers, runtime implementers", "level": "Architecture", "searchIntent": "Machine Intelligence Runtime definition architecture runtime", "lastReviewedUtc": "2026-06-27", "lastMaterialChangeUtc": "2026-06-27", "parent": "runtime-types", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "semantic-runtime-engine", "title": "Semantic Runtime Engine", "url": "https://aruntime.com/runtime-types/semantic-runtime-engine/", "summary": "Runtime layer that manages meaning-bearing data structures such as embeddings, semantic tokens, entities, relationships, knowledge-graph paths, and compiled intent.", "contentType": "Reference page", "contentStatus": "Emerging proposal", "audience": "AI architects, platform engineers, runtime implementers", "level": "Architecture", "searchIntent": "Semantic Runtime Engine definition architecture runtime", "lastReviewedUtc": "2026-06-27", "lastMaterialChangeUtc": "2026-06-27", "parent": "runtime-types", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "cognitive-runtime-environment", "title": "Cognitive Runtime Environment", "url": "https://aruntime.com/runtime-types/cognitive-runtime-environment/", "summary": "Runtime layer for long-horizon reasoning, memory, context paging, planning loops, task decomposition, reasoning budgets, and recovery around a language model.", "contentType": "Reference page", "contentStatus": "Emerging proposal", "audience": "AI architects, platform engineers, runtime implementers", "level": "Architecture", "searchIntent": "Cognitive Runtime Environment definition architecture runtime", "lastReviewedUtc": "2026-06-27", "lastMaterialChangeUtc": "2026-06-27", "parent": "runtime-types", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" }, { "id": "neural-execution-engine", "title": "Neural Execution Engine", "url": "https://aruntime.com/runtime-types/neural-execution-engine/", "summary": "Low-level runtime and compiler boundary for neural graphs, tensor programs, backend scheduling, memory planning, execution providers, and hardware abstraction.", "contentType": "Reference page", "contentStatus": "Emerging proposal", "audience": "AI architects, platform engineers, runtime implementers", "level": "Architecture", "searchIntent": "Neural Execution Engine definition architecture runtime", "lastReviewedUtc": "2026-06-27", "lastMaterialChangeUtc": "2026-06-27", "parent": "runtime-types", "canonicalEvidence": [ "visible-page", "content-catalog", "llms-full" ], "robots": "index,follow" } ] }