{"schema_version":"newruntime-topic-hub-v0.2","type":"topic_hub","stable_id":"topic_hub:infrastructure","slug":"infrastructure","title":"Infrastructure - New Runtime","description":"A New Runtime topic hub collecting signals, patterns, field notes, and public sources about infrastructure.","retrieval_nugget":"A New Runtime topic hub collecting signals, patterns, field notes, and public sources about infrastructure. Infrastructure is tracked here as an evidence-linked topic, not as a static glossary entry. The page connects raw observations to pattern hypotheses, longer analysis, and public sources. Use it as the canonical landing page before drilling into individual records.","answer":["Infrastructure is tracked here as an evidence-linked topic, not as a static glossary entry.","The page connects raw observations to pattern hypotheses, longer analysis, and public sources.","Use it as the canonical landing page before drilling into individual records."],"search_intents":["infrastructure","infrastructure AI agents","infrastructure software"],"status":"featured","last_updated":"2026-07-31","record_date":"2026-07-31","date_kind":"last_updated","counts":{"total":10,"signals":1,"patterns":0,"posts":9,"atlas":0,"sources":30},"routes":{"html":"https://newruntime.com/topics/infrastructure/","markdown":"https://newruntime.com/topics/infrastructure.md","json":"https://newruntime.com/topics/infrastructure.json"},"source_urls":["https://arxiv.org/abs/2606.23050","https://developers.cloudflare.com/sandbox/tutorials/devin-outposts/","https://huggingface.co/baidu/Unlimited-OCR","https://modal.com/blog/devin-outposts-run-devin-in-modal-sandoxes","https://openclaw.ai/blog/extended-stable-releases-and-maturity-scorecards","https://render.com/","https://render.com/docs/deploys","https://render.com/platform","https://vercel.com/changelog/latest-mcp-spec-now-supported-in-mcp-handler","https://vercel.com/changelog/regional-inference-now-available-on-ai-gateway","https://vercel.com/changelog/run-multiple-isolated-agents-in-a-single-sandbox","https://vercel.com/changelog/vercel-connect-preset-connectors"],"top_sources":["https://arxiv.org/abs/2606.23050","https://developers.cloudflare.com/sandbox/tutorials/devin-outposts/","https://huggingface.co/baidu/Unlimited-OCR","https://modal.com/blog/devin-outposts-run-devin-in-modal-sandoxes","https://openclaw.ai/blog/extended-stable-releases-and-maturity-scorecards","https://render.com/","https://render.com/docs/deploys","https://render.com/platform","https://vercel.com/changelog/latest-mcp-spec-now-supported-in-mcp-handler","https://vercel.com/changelog/regional-inference-now-available-on-ai-gateway","https://vercel.com/changelog/run-multiple-isolated-agents-in-a-single-sandbox","https://vercel.com/changelog/vercel-connect-preset-connectors"],"evidence_records":[{"kind":"Field Note","stable_id":"post:langsmith-llm-gateway-runtime-controls","slug":"langsmith-llm-gateway-runtime-controls","title":"LangSmith LLM Gateway Puts Runtime Controls Between Agents and Models","date":"2026-07-31","record_date":"2026-07-31","date_kind":"updated_or_published_at","source_count":4,"url":"https://newruntime.com/posts/langsmith-llm-gateway-runtime-controls/"},{"kind":"Field Note","stable_id":"post:vercel-passport-agent-identity-boundary","slug":"vercel-passport-agent-identity-boundary","title":"Vercel Passport Makes Identity a Deployment Boundary","date":"2026-07-31","record_date":"2026-07-31","date_kind":"updated_or_published_at","source_count":2,"url":"https://newruntime.com/posts/vercel-passport-agent-identity-boundary/"},{"kind":"Field Note","stable_id":"post:vercel-sandbox-multi-user-agents","slug":"vercel-sandbox-multi-user-agents","title":"Vercel Sandbox Adds Unix Boundaries for Multi-Agent Work","date":"2026-07-31","record_date":"2026-07-31","date_kind":"updated_or_published_at","source_count":2,"url":"https://newruntime.com/posts/vercel-sandbox-multi-user-agents/"},{"kind":"Field Note","stable_id":"post:llm-inference-backpressure-before-autoscaling","slug":"llm-inference-backpressure-before-autoscaling","title":"LLM Inference Fails Quietly Before It Fails Loudly","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","source_count":1,"url":"https://newruntime.com/posts/llm-inference-backpressure-before-autoscaling/"},{"kind":"Field Note","stable_id":"post:openclaw-extended-stable-maturity-scorecard","slug":"openclaw-extended-stable-maturity-scorecard","title":"OpenClaw Adds an Extended-Stable Channel and Maturity Scorecard","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","source_count":2,"url":"https://newruntime.com/posts/openclaw-extended-stable-maturity-scorecard/"},{"kind":"Field Note","stable_id":"post:unlimited-ocr-long-horizon-parsing","slug":"unlimited-ocr-long-horizon-parsing","title":"Unlimited OCR Treats a Long Document as One Parsing Horizon","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","source_count":2,"url":"https://newruntime.com/posts/unlimited-ocr-long-horizon-parsing/"},{"kind":"Field Note","stable_id":"post:vercel-mcp-handler-stateless-protocol-bridge","slug":"vercel-mcp-handler-stateless-protocol-bridge","title":"Vercel's mcp-handler 2.0 Makes MCP Servers More Stateless","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","source_count":2,"url":"https://newruntime.com/posts/vercel-mcp-handler-stateless-protocol-bridge/"},{"kind":"Field Note","stable_id":"post:vercel-agent-platform-control-plane","slug":"vercel-agent-platform-control-plane","title":"Vercel's Agent Platform Surface Is Becoming a Control Plane","date":"2026-07-29","record_date":"2026-07-29","date_kind":"updated_or_published_at","source_count":8,"url":"https://newruntime.com/posts/vercel-agent-platform-control-plane/"},{"kind":"Field Note","stable_id":"post:devin-outposts-agent-execution-plane","slug":"devin-outposts-agent-execution-plane","title":"Devin Outposts Splits the Agent Brain from the Execution Plane","date":"2026-07-22","record_date":"2026-07-22","date_kind":"updated_or_published_at","source_count":4,"url":"https://newruntime.com/posts/devin-outposts-agent-execution-plane/"},{"kind":"Raw Signal","stable_id":"signal:render-packages-deployment-primitives-for-agent-workloads","slug":"render-packages-deployment-primitives-for-agent-workloads","title":"Render Packages Deployment Primitives for Agent Workloads","date":"2026-07-11","record_date":"2026-07-11","date_kind":"observed_at","source_count":3,"url":"https://newruntime.com/signals/render-packages-deployment-primitives-for-agent-workloads/"}],"patterns":[],"field_notes":[{"kind":"Field Note","stable_id":"post:langsmith-llm-gateway-runtime-controls","slug":"langsmith-llm-gateway-runtime-controls","title":"LangSmith LLM Gateway Puts Runtime Controls Between Agents and Models","description":"LangSmith LLM Gateway turns spend caps, rate limits, fallbacks, redaction, and provider routing into one governed layer for production agents.","date":"2026-07-31","record_date":"2026-07-31","date_kind":"updated_or_published_at","topics":["agents","api-design","infrastructure","security"],"source_count":4,"url":"https://newruntime.com/posts/langsmith-llm-gateway-runtime-controls/"},{"kind":"Field Note","stable_id":"post:vercel-passport-agent-identity-boundary","slug":"vercel-passport-agent-identity-boundary","title":"Vercel Passport Makes Identity a Deployment Boundary","description":"Vercel Passport is now generally available, adding verified identity tokens, group claims, audit events, and automation bypasses to protected deployments.","date":"2026-07-31","record_date":"2026-07-31","date_kind":"updated_or_published_at","topics":["api-design","enterprise-ai","infrastructure","security"],"source_count":2,"url":"https://newruntime.com/posts/vercel-passport-agent-identity-boundary/"},{"kind":"Field Note","stable_id":"post:vercel-sandbox-multi-user-agents","slug":"vercel-sandbox-multi-user-agents","title":"Vercel Sandbox Adds Unix Boundaries for Multi-Agent Work","description":"Vercel Sandbox now supports multiple Linux users and groups, giving each agent a private home directory plus an explicit shared workspace.","date":"2026-07-31","record_date":"2026-07-31","date_kind":"updated_or_published_at","topics":["agents","developer-tools","infrastructure","security"],"source_count":2,"url":"https://newruntime.com/posts/vercel-sandbox-multi-user-agents/"},{"kind":"Field Note","stable_id":"post:llm-inference-backpressure-before-autoscaling","slug":"llm-inference-backpressure-before-autoscaling","title":"LLM Inference Fails Quietly Before It Fails Loudly","description":"Akamai's vLLM load tests show why 200 OK is a weak health signal and why bounded admission, context limits, and an external queue should precede autoscaling.","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","topics":["ai-models","api-design","infrastructure"],"source_count":1,"url":"https://newruntime.com/posts/llm-inference-backpressure-before-autoscaling/"},{"kind":"Field Note","stable_id":"post:openclaw-extended-stable-maturity-scorecard","slug":"openclaw-extended-stable-maturity-scorecard","title":"OpenClaw Adds an Extended-Stable Channel and Maturity Scorecard","description":"OpenClaw's extended-stable releases and maturity scorecard show agent runtimes moving toward support channels, backports, feature maturity, and production E2E tests.","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","topics":["agents","infrastructure","release-engineering","verification"],"source_count":2,"url":"https://newruntime.com/posts/openclaw-extended-stable-maturity-scorecard/"},{"kind":"Field Note","stable_id":"post:unlimited-ocr-long-horizon-parsing","slug":"unlimited-ocr-long-horizon-parsing","title":"Unlimited OCR Treats a Long Document as One Parsing Horizon","description":"Baidu's Unlimited OCR replaces full decoder attention with a reference sliding window so multi-page parsing can keep a constant KV cache across long outputs.","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","topics":["ai-models","infrastructure"],"source_count":2,"url":"https://newruntime.com/posts/unlimited-ocr-long-horizon-parsing/"},{"kind":"Field Note","stable_id":"post:vercel-mcp-handler-stateless-protocol-bridge","slug":"vercel-mcp-handler-stateless-protocol-bridge","title":"Vercel's mcp-handler 2.0 Makes MCP Servers More Stateless","description":"mcp-handler 2.0 supports the 2026-07-28 MCP spec while keeping older Streamable HTTP clients on the same endpoint and removing Redis or session-storage requirements.","date":"2026-07-30","record_date":"2026-07-30","date_kind":"updated_or_published_at","topics":["api-design","developer-tools","infrastructure","mcp"],"source_count":2,"url":"https://newruntime.com/posts/vercel-mcp-handler-stateless-protocol-bridge/"},{"kind":"Field Note","stable_id":"post:vercel-agent-platform-control-plane","slug":"vercel-agent-platform-control-plane","title":"Vercel's Agent Platform Surface Is Becoming a Control Plane","description":"Regional inference, scoped Connect tokens, sandbox forking, and Python WebSockets show Vercel turning agent infrastructure into runtime control surfaces.","date":"2026-07-29","record_date":"2026-07-29","date_kind":"updated_or_published_at","topics":["agents","api-design","developer-tools","infrastructure"],"source_count":8,"url":"https://newruntime.com/posts/vercel-agent-platform-control-plane/"},{"kind":"Field Note","stable_id":"post:devin-outposts-agent-execution-plane","slug":"devin-outposts-agent-execution-plane","title":"Devin Outposts Splits the Agent Brain from the Execution Plane","description":"Devin Outposts moves command execution, repository access, and sandbox lifecycle into customer-controlled infrastructure while the agent loop remains in Cognition's cloud.","date":"2026-07-22","record_date":"2026-07-22","date_kind":"updated_or_published_at","topics":["agent-runtime","coding-agents","infrastructure"],"source_count":4,"url":"https://newruntime.com/posts/devin-outposts-agent-execution-plane/"}],"raw_signals":[{"kind":"Raw Signal","stable_id":"signal:render-packages-deployment-primitives-for-agent-workloads","slug":"render-packages-deployment-primitives-for-agent-workloads","title":"Render Packages Deployment Primitives for Agent Workloads","description":"Render combines services, workers, databases, cron jobs, previews, and infrastructure definitions into a deployment surface suitable for long-running agent systems.","date":"2026-07-11","record_date":"2026-07-11","date_kind":"observed_at","topics":["agent-runtime","deployment","infrastructure"],"source_count":3,"metric":"notable","url":"https://newruntime.com/signals/render-packages-deployment-primitives-for-agent-workloads/"}],"atlas_records":[],"next_reads":[{"type":"related_material","path":"/posts/langsmith-llm-gateway-runtime-controls/","reason":"Continue through the Infrastructure topic.","url":"https://newruntime.com/posts/langsmith-llm-gateway-runtime-controls/","title":"LangSmith LLM Gateway Puts Runtime Controls Between Agents and Models","media_type":"text/html"},{"type":"related_material","path":"/posts/vercel-passport-agent-identity-boundary/","reason":"Continue through the Infrastructure topic.","url":"https://newruntime.com/posts/vercel-passport-agent-identity-boundary/","title":"Vercel Passport Makes Identity a Deployment Boundary","media_type":"text/html"},{"type":"related_material","path":"/posts/vercel-sandbox-multi-user-agents/","reason":"Continue through the Infrastructure topic.","url":"https://newruntime.com/posts/vercel-sandbox-multi-user-agents/","title":"Vercel Sandbox Adds Unix Boundaries for Multi-Agent Work","media_type":"text/html"},{"type":"related_material","path":"/posts/llm-inference-backpressure-before-autoscaling/","reason":"Continue through the Infrastructure topic.","url":"https://newruntime.com/posts/llm-inference-backpressure-before-autoscaling/","title":"LLM Inference Fails Quietly Before It Fails Loudly","media_type":"text/html"},{"type":"related_material","path":"/posts/openclaw-extended-stable-maturity-scorecard/","reason":"Continue through the Infrastructure topic.","url":"https://newruntime.com/posts/openclaw-extended-stable-maturity-scorecard/","title":"OpenClaw Adds an Extended-Stable Channel and Maturity Scorecard","media_type":"text/html"}]}