Kevin Cearns writes about AI infrastructure, agents, self-hosted models and the platforms underneath them. Long-form engineering guides, a portfolio of systems built, and a model card instead of a résumé.https://kcearns.tech/en-cahttps://kcearns.tech/writing/self-hosting-buzz-local-community/https://kcearns.tech/writing/self-hosting-buzz-local-community/Buzz is a self-hostable workspace where people and AI agents share the same rooms, built as a Nostr relay. A hands-on walkthrough: standing up a local community, the host-binding gotcha that will stop you cold, and adding an agent backed by OpenRouter, a local Hermes model, or Claude Code.Sun, 26 Jul 2026 00:00:00 GMTbuzznostrself-hostingagentsrustai-infrastructurehttps://kcearns.tech/writing/eve-firecracker-fleet-recap/https://kcearns.tech/writing/eve-firecracker-fleet-recap/A capstone to the seven-part series on running eve.dev agents on a fleet of Firecracker microVMs in AWS. The whole platform in one picture, a guided tour of the parts, and the design threads — bare-metal constraints, desired-vs-actual state, event-driven placement, and packing-as-economics — that hold it together.Mon, 20 Jul 2026 00:00:00 GMTawsaws-cdkfirecrackereveagentstypescriptplatform-engineeringai-infrastructurehttps://kcearns.tech/writing/eve-firecracker-fleet-agent-images/https://kcearns.tech/writing/eve-firecracker-fleet-agent-images/Part 3 of the hands-on series. We turn an ordinary eve agent directory into a bootable ext4 rootfs with a build-rootfs.sh, store it in a versioned S3 artifact bucket the hosts pull from, inject secrets per-microVM with MMDS, and use Firecracker snapshots to turn a cold multi-second boot into a warm sub-second resume.Sun, 19 Jul 2026 00:00:00 GMTawsaws-cdkfirecrackereveagentstypescripts3ai-infrastructurehttps://kcearns.tech/writing/eve-firecracker-fleet-control-plane/https://kcearns.tech/writing/eve-firecracker-fleet-control-plane/Part 4 of the hands-on series. We build the scheduler that turns a deploy request into a running agent — API Gateway and Lambda over a DynamoDB registry of hosts, agents, and placements, a race-safe bin-packing placement algorithm, and EventBridge decoupling the API from the work, all in AWS CDK.Sun, 19 Jul 2026 00:00:00 GMTawsaws-cdkfirecrackereveagentstypescriptlambdadynamodbai-infrastructurehttps://kcearns.tech/writing/eve-firecracker-fleet-deploy-workflow/https://kcearns.tech/writing/eve-firecracker-fleet-deploy-workflow/Part 6 of the hands-on series. We turn the moving parts into one command — a deploy CLI that chains build, upload, place, and wait-for-URL; IAM auth on the control-plane API; and a GitHub Actions pipeline that ships an agent on merge and gives every pull request its own preview agent.Sun, 19 Jul 2026 00:00:00 GMTawsaws-cdkfirecrackereveagentstypescriptgithub-actionscicdai-infrastructurehttps://kcearns.tech/writing/eve-firecracker-fleet-host-fleet/https://kcearns.tech/writing/eve-firecracker-fleet-host-fleet/Part 2 of the hands-on series. We put the first machines into the network from Part 1 — an Auto Scaling Group of bare-metal EC2 hosts, a launch template whose user data installs Firecracker and a host-agent daemon, the IAM role each host runs under, and the capacity model that decides how many agents a host can hold.Sun, 19 Jul 2026 00:00:00 GMTawsaws-cdkfirecrackereveagentstypescriptec2autoscalingai-infrastructurehttps://kcearns.tech/writing/eve-firecracker-fleet-operations/https://kcearns.tech/writing/eve-firecracker-fleet-operations/The final part of the series. We make the fleet operable — event-driven host autoscaling with lifecycle-hook draining, a reconciliation loop that reschedules agents off a dead host, per-agent logs and metrics rolled up across the fleet, and the FinOps view that turns packing density into cost per agent.Sun, 19 Jul 2026 00:00:00 GMTawsaws-cdkfirecrackereveagentstypescriptautoscalingobservabilityfinopsai-infrastructurehttps://kcearns.tech/writing/eve-firecracker-fleet-routing/https://kcearns.tech/writing/eve-firecracker-fleet-routing/Part 5 of the hands-on series. We make a placed agent reachable — per-microVM tap devices and NAT on each host, an internet-facing ALB with a wildcard certificate, a per-agent subdomain scheme, and a host-local front proxy that resolves an agent to its microVM wherever the control plane placed it.Sun, 19 Jul 2026 00:00:00 GMTawsaws-cdkfirecrackereveagentstypescriptalbnetworkingai-infrastructurehttps://kcearns.tech/writing/eve-agent-firecracker-aws-cdk/https://kcearns.tech/writing/eve-agent-firecracker-aws-cdk/A beginner's walkthrough of provisioning bare-metal AWS infrastructure with CDK TypeScript, then booting a Firecracker microVM to self-host a Vercel eve agent.Sat, 18 Jul 2026 00:00:00 GMTawsaws-cdkfirecrackereveagentstypescriptai-developmentobservabilityopentelemetryfinopshttps://kcearns.tech/writing/eve-firecracker-fleet-architecture/https://kcearns.tech/writing/eve-firecracker-fleet-architecture/Part 1 of a hands-on series turning a single Firecracker host into a fleet that hosts eve.dev agents on demand. We map the whole platform — a control plane that places agents onto bare-metal hosts, and a routing layer that gets requests back to them — then provision the VPC, subnets, and security groups in AWS CDK.Sat, 18 Jul 2026 00:00:00 GMTawsaws-cdkfirecrackereveagentstypescriptai-infrastructurehttps://kcearns.tech/writing/vercel-eve-agent-quickstart/https://kcearns.tech/writing/vercel-eve-agent-quickstart/A short, hands-on walkthrough of scaffolding, running, and deploying an AI agent with Vercel's open-source eve framework.Thu, 09 Jul 2026 00:00:00 GMTai-developmentverceleveagentshttps://kcearns.tech/writing/eks-hybrid-llm-platform-inference/https://kcearns.tech/writing/eks-hybrid-llm-platform-inference/Part 5 of our hands-on EKS series. We deploy vLLM model servers on the GPU pool from Part 4, load Qwen2.5-7B model weights from Amazon S3 via an init container, and wire KEDA autoscaling that scales replicas with live queue depth and drives GPU nodes to zero overnight.Sun, 07 Jun 2026 00:00:00 GMTekskubernetesaws-cdkvllmkedagpuautoscalingllmai-infrastructuretypescripthttps://kcearns.tech/writing/eks-hybrid-llm-platform-observability/https://kcearns.tech/writing/eks-hybrid-llm-platform-observability/Part 7 of our hands-on EKS series. We instrument the TypeScript router with OpenTelemetry, upgrade Prometheus to kube-prometheus-stack for GPU and vLLM metrics, add Grafana Tempo for distributed traces, and wire Langfuse so every request shows its backend, token count, and dollar cost.Sun, 07 Jun 2026 00:00:00 GMTekskubernetesaws-cdkopentelemetryprometheusgrafanalangfuseobservabilitytypescriptai-infrastructurehttps://kcearns.tech/writing/eks-hybrid-llm-platform-router/https://kcearns.tech/writing/eks-hybrid-llm-platform-router/Part 6 of our hands-on EKS series. We build a TypeScript/Hono router that sits in front of both vLLM and the Anthropic API, routes each request to the right backend based on model name and complexity heuristics, and falls back to cloud when the local model is cold-starting.Sun, 07 Jun 2026 00:00:00 GMTekskubernetesaws-cdkhonotypescriptllmroutinghybrid-aiai-infrastructurehttps://kcearns.tech/writing/eks-hybrid-llm-platform-testing/https://kcearns.tech/writing/eks-hybrid-llm-platform-testing/The final part of our EKS series. We write integration tests with Vitest, load-test the ALB with k6, build three real-world TypeScript workloads that prove the hybrid routing works, and use the Grafana and Langfuse dashboards from Part 7 to verify the platform under traffic.Sun, 07 Jun 2026 00:00:00 GMTekskubernetesaws-cdkvitestk6testingtypescriptllmai-infrastructurehttps://kcearns.tech/writing/eks-hybrid-llm-platform-addons/https://kcearns.tech/writing/eks-hybrid-llm-platform-addons/Part 4 of our hands-on EKS series. We install the two add-ons every production EKS cluster needs: the AWS Load Balancer Controller so Kubernetes Ingress objects provision real ALBs, and Karpenter for cost-aware autoscaling — including the GPU NodePool that scales to zero between inference workloads.Sat, 06 Jun 2026 00:00:00 GMTekskubernetesaws-cdkkarpenterload-balancer-controllerautoscalingirsaai-infrastructuretypescripthttps://kcearns.tech/writing/eks-hybrid-llm-platform-node-groups/https://kcearns.tech/writing/eks-hybrid-llm-platform-node-groups/Part 3 of our hands-on EKS series. We add worker nodes to the empty cluster from Part 2: a CPU system pool for add-ons and the hybrid router, a GPU pool for vLLM model servers, the NVIDIA device plugin DaemonSet, and the taints and labels that make scheduling predictable.Sat, 06 Jun 2026 00:00:00 GMTekskubernetesaws-cdkgpunvidianode-groupsai-infrastructuretypescripthttps://kcearns.tech/writing/eks-hybrid-llm-platform-control-plane/https://kcearns.tech/writing/eks-hybrid-llm-platform-control-plane/Part 2 of our hands-on EKS series. We provision the EKS cluster into the VPC from Part 1, wire up OIDC federation and IRSA so pods authenticate without static credentials, and end with a working kubectl connection to a real cluster.Sat, 30 May 2026 00:00:00 GMTekskubernetesaws-cdkiamirsaoidcai-infrastructuretypescripthttps://kcearns.tech/writing/securing-self-hosted-llm-agents-kubernetes/https://kcearns.tech/writing/securing-self-hosted-llm-agents-kubernetes/Harden self-hosted vLLM and AI agents on Kubernetes: an auth/rate-limit gateway, gVisor tool sandboxing, prompt-injection guardrails, scoped secrets, and signed model weights — mapped to the OWASP LLM Top 10.Fri, 29 May 2026 00:00:00 GMTsecurityaiagentskubernetesllmprompt-injectionsupply-chainhttps://kcearns.tech/writing/eks-hybrid-llm-platform-architecture-network/https://kcearns.tech/writing/eks-hybrid-llm-platform-architecture-network/Part 1 of a hands-on series building the EKS-based hybrid LLM platform referenced throughout this blog. We map out the full architecture, then provision the VPC, subnets, NAT, and VPC endpoints with AWS CDK — the network foundation every later part builds on.Sun, 24 May 2026 00:00:00 GMTekskubernetesaws-cdkllmai-infrastructurehybrid-aivpctypescripthttps://kcearns.tech/writing/personal-ai-dev-environment/https://kcearns.tech/writing/personal-ai-dev-environment/The production patterns we deploy for teams — hybrid cloud/local routing, self-hosted models, agent orchestration — scaled down to a single developer's workstation. A practical guide to building a personal AI dev environment with Ollama, Claude Code, and a local router that keeps your token bill near zero.Sat, 23 May 2026 00:00:00 GMTaillmlocal-modelsollamaclaude-codedeveloper-toolshttps://kcearns.tech/writing/multi-agent-orchestration-frontier-local-models/https://kcearns.tech/writing/multi-agent-orchestration-frontier-local-models/How to orchestrate a fleet of AI agents using a shared task queue — frontier models like Claude handle planning and decomposition, while a local Kubernetes worker pool runs the high-volume execution tasks. Covers the task ledger, dynamic task creation, lane-based routing, and KEDA autoscaling.Fri, 22 May 2026 00:00:00 GMTaiagentsorchestrationkubernetesllmhybridhttps://kcearns.tech/writing/llm-observability-kubernetes/https://kcearns.tech/writing/llm-observability-kubernetes/How to instrument self-hosted and hybrid LLM workloads with OpenTelemetry, Prometheus, and Langfuse — tracking time-to-first-token, tokens per second, GPU utilization, and unit economics down to the individual request.Thu, 21 May 2026 00:00:00 GMTkubernetesllmobservabilityopentelemetryfinopsai-infrastructurehttps://kcearns.tech/writing/hybrid-ai-local-cloud-models/https://kcearns.tech/writing/hybrid-ai-local-cloud-models/How to cut your AI costs by 60-80% using a hybrid approach — Claude or GPT for planning and complex reasoning, local models like Llama and Qwen for execution tasks like code generation, summarization, and data extraction.Thu, 14 May 2026 00:00:00 GMTaillmcost-optimizationlocal-modelsollamahttps://kcearns.tech/writing/self-hosting-llms-kubernetes/https://kcearns.tech/writing/self-hosting-llms-kubernetes/How to deploy, serve, and autoscale open-source large language models on Kubernetes with vLLM — from GPU node pools and deployment manifests to KEDA-based autoscaling and production guardrails.Fri, 03 Apr 2026 00:00:00 GMTkubernetesllmgpuai-infrastructureself-hostinghttps://kcearns.tech/writing/container-security-kubernetes-trivy-falco-kyverno/https://kcearns.tech/writing/container-security-kubernetes-trivy-falco-kyverno/Most Kubernetes clusters are running containers with known vulnerabilities, no runtime monitoring, and no policy enforcement. Here is how to fix that with three open-source tools.Sun, 08 Feb 2026 00:00:00 GMTkubernetessecuritytrivyfalcokyvernocontainershttps://kcearns.tech/writing/ai-driven-kubernetes-monitoring-scaling/https://kcearns.tech/writing/ai-driven-kubernetes-monitoring-scaling/How to move beyond static thresholds and use AI-driven observability to detect anomalies, predict traffic patterns, and automate scaling decisions across your Kubernetes infrastructure.Fri, 07 Feb 2025 00:00:00 GMTkubernetesaimonitoringautoscalingobservabilityhttps://kcearns.tech/writing/cicd-pipeline-dagger-kubernetes/https://kcearns.tech/writing/cicd-pipeline-dagger-kubernetes/A practical guide to building a containerized CI/CD pipeline using Dagger's TypeScript SDK — from local Kind clusters to production EKS with GitHub Actions, AWS CDK, and multi-environment promotion.Wed, 29 Jan 2025 00:00:00 GMTdaggerkubernetescicdhelmeksgithub-actionsaws-cdkhttps://kcearns.tech/writing/building-feature-flag-service-claude-code/https://kcearns.tech/writing/building-feature-flag-service-claude-code/How we built FlagSignals, a full-stack feature flag platform with A/B testing and billing, using AI-assisted development.Wed, 22 Jan 2025 00:00:00 GMTfeature-flagsai-developmentnextjssupabasehttps://kcearns.tech/writing/gpu-cost-optimization-kubernetes/https://kcearns.tech/writing/gpu-cost-optimization-kubernetes/Learn how to reduce GPU infrastructure costs by up to 60% with proper Kubernetes scheduling, time-slicing, and right-sizing strategies.Wed, 15 Jan 2025 00:00:00 GMTkubernetesgpucost-optimizationinfrastructure