Kubernetes
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 8
- Factory launches OpenCompute, a self-hosted agent sandbox orchestrator
On October 14, 2026, Factory introduced OpenCompute, a self-hosted orchestrator for agent sandboxes now in private preview that runs on the customer's choice of runtime, including Kubernetes, AWS Lambda MicroVMs, EC2 and in-house platforms. It connects to the Factory backend over an outbound, TLS-secured WebSocket with no inbound firewall ports required; the Go control plane records desired and observed state in a Postgres database inside the customer's environment, uses a declarative reconciler, and splits each provider into a standalone gRPC driver with a required Core conformance profile plus optional Suspend, Snapshot and Fork profiles. Factory says its first customer went from prototype to a first sandbox running in its own data center in six weeks, and the company plans to open-source OpenCompute, including its contracts, conformance tests and driver model.
Factory News · 🔥 0 - Intel launches inference microservices for Xeon processors
Intel announced Intel Inference Microservices, a containerized microservice offering for large language model inference aimed at letting enterprises get tuned inference on Xeon processors they already own without days of manual hardware optimization. Each microservice is a standalone container serving one model over an OpenAI-compatible API; at startup it detects the processor generation, assigned cores, NUMA layout and built-in accelerators such as AMX, AVX-512, AVX2 and VNNI, then applies a validated configuration profile. The first versions are based on the vLLM engine with BF16 precision, run in Docker or Kubernetes 1.24+ on 4th, 5th or 6th Gen Intel Xeon with 32GB RAM suggested. Intel says later versions will add Helm charts, a Kubernetes Operator, more engines and precisions, and that the same model will extend to Intel GPUs including the Crescent Island data-center inference GPU.
IT之家 AI · 🔥 0 - Google adds MCP support to Apigee hybrid, running the data plane in customer clusters
Google's developer blog announced that Apigee hybrid 1.17.0 supports the Model Context Protocol: users create an MCP Discovery Proxy from an OpenAPI 3.0.x specification, each operation in the spec becomes an MCP tool, and agents discover and call tools over JSON-RPC using tools/list and tools/call without writing or operating a separate MCP server. The post says the MCP data plane runs inside the customer's own Kubernetes cluster, MCP request traffic never leaves the cluster, and configuration is pulled by a sidecar inside the cluster, so the Apigee control plane never initiates a connection into the customer's network. MCP is optional and off by default; enabling it requires setting enableMcpServer via Helm and upgrading the apigee-operator chart first and the apigee-org chart second.
Google Developers Blog · 🔥 0 - Nvidia open-sources full Run:ai platform under Apache 2.0 as part of DSX AI Factory
Nvidia released the complete Run:ai platform as open source under the Apache 2.0 license on Oct. 13, 2026, folding it into the Nvidia DSX AI Factory Platform so organizations can deploy GPU scheduling, resource management and AI workload orchestration on Kubernetes without buying a Run subscription. The release includes the full self-hosted control plane plus four independently adoptable modules — KAI Scheduler, GPU Fractioning Operator, KAI Resource Management and Workload Map — with eight DSX ecosystem partners including Crusoe, Mirantis, Nebius, OpenNebula Systems, Rafay, Saturn Cloud, Spectro Cloud and vCluster integrating the platform into their offerings. Enterprise support, service-level commitments and entitlements remain paid options, and free-version users must handle their own infrastructure, upgrades, security monitoring and incident response.
TechRepublic · 🔥 0 - SUSE unveils private enterprise AI strategy, AI Factory with NVIDIA and Liz ops agent
SUSE announced an "enterprise private AI" strategy and an AI Factory offering with NVIDIA that combines NVIDIA AI Enterprise with SUSE's infrastructure and security governance capabilities, for AI workloads on-premises, in multi-cloud and in offline environments. SUSE says the combination can cut deployment time from months to days, though it acknowledges actual timelines depend on existing systems, data readiness and integration complexity. The release also includes Liz, a Kubernetes operations agent integrated into Rancher Prime that supports Chinese-language interaction and troubleshooting under a human-in-the-loop design; the China version is adapted to models including Qwen, DeepSeek, Kimi, Zhipu and MiniMax. SUSE also floated a possible evolution toward a "Token Factory," described as a product direction rather than a delivered capability.
InfoQ 中文 AI&大模型 · 🔥 0 - From demo to production: what an agent harness actually adds
The piece frames an agent as "model + harness" and splits the harness into a development half (memory, tools and MCP, retrieval, prompt orchestration) and an operations half (observability, evals, guardrails, routing, cost control, deployment and scaling) — capabilities the model itself does not provide. It then builds the same finance agent, FinBot, two ways: a managed Amazon Bedrock AgentCore Harness configured via CreateHarness/InvokeHarness calls, with per-session Firecracker microVMs, managed memory and automatic tracing; and a self-managed LangChain agent on the reader's own Kubernetes cluster behind the open-source Agent Router (formerly Envoy AI Gateway). The trade-offs come down to where provider credentials live, who carries the operational burden, and whether you pay a vendor bill or infrastructure plus engineering time.
InfoQ 中文 AI&大模型 · 🔥 0 - AWS details multi-tenant GPU cluster sharing on SageMaker HyperPod
An AWS Machine Learning Blog post lays out a reference architecture for letting multiple teams share a single Amazon SageMaker HyperPod (EKS) GPU cluster while preserving isolation and fairness. It uses AWS IAM Identity Center for centralized authentication (federating with Microsoft Entra ID via SCIM provisioning and SAML 2.0), per-team SageMaker AI domains and execution roles, and Kubernetes namespaces for workload isolation. HyperPod Task Governance handles fair resource allocation, namespace-level cost allocation provides per-team chargeback visibility, and storage is split across FSx for Lustre or OpenZFS directories and S3 buckets.
AWS Machine Learning Blog · 🔥 0 - Stacklok's Mecatl: a Kubernetes-style cloud-native harness for agents
Stacklok, founded by Kubernetes creators Craig McLuckie and Joe Beda, pivoted from software supply chain security to Kubernetes-based agentic infrastructure. Its open source “cloud-native harness” Mecatl, started in June, separates the agent loop from tool execution, session management and memory; the companion open source project ToolHive runs and governs MCP servers on Kubernetes. The company says its AI Gateway is not yet open sourced but is on the roadmap, with an “enterprise spine” control plane as the commercial product.
Latent Space · 🔥 0
Experience and discussion from the community
Share my Kubernetes experienceAsk about Kubernetes
Nobody has shared their experience with Kubernetes yet.