#kubernetes

🔊 Hear how developers actually pronounce kubectl, nginx, GIF & 1,900+ tech terms. Sourced dictionary + CLI + VS Code + GitHub Action + MCP + Agent Skill.

A Kubernetes lab that reproduces real production incidents on a live, instrumented microservice stack — for testing root-cause-analysis tools and agents.

The self-improving SRE agent

A Kubernetes-native operator for platform teams to inspect, debug, and explore files on idle or active Persistent Volume Claims (PVCs).

Model-agnostic DevOps AI agent harness: policy, approvals, audit and rollback enforced outside the LLM. Works with Claude Code, OpenCode, Cursor, Copilot and any MCP client.

Agent Skills and an MCP server for GPU performance profiling, benchmarking, optimization, and reporting, with an inference focus.

Multi-cluster Kubernetes dashboard — the whole UI baked into one Go binary. Resource lists stream binary MessagePack deltas over WebSocket; no polling, no pagination, virtualised end-to-end. Inline scale, restart, rollback, exec, logs, port-forward, YAML edit. Prometheus + metrics-server. Docker, Helm or raw manifests.

Freelens Agent Bridge Extension

Turn an architecture spec into editable diagrams with official vendor service icons (Azure/AWS/GCP/K8s) - .pdf/.drawio/.vsdx. Usable by AI agents via skill or MCP server.

Self-hostable managed agents harness. Author YAML manifests; Felix compiles them into governed agents with durable fibers, memory, skills, eval, approvals, and sandboxes — over OpenAI, A2A, MCP, and SSE. Fork, rewind, and steer runs. Docker, Helm, AWS, or GCP.

AI governance and edge infrastructure platform with HTTP/3, OpenTelemetry tracing, adaptive load shedding, circuit breakers and Kubernetes deployment support.

Kubernetes observability suite: a pod/container metadata service plus a per-node agent that tails container logs, scrapes Prometheus targets, cadvisor, node metrics and journald, enriches everything with pod metadata, and exports OTLP

2026 AI Dev Sandbox: Real Env Injection, Live Traffic Replay & Network Mirroring

Local-first Kubernetes platform for private LLM and coding-agent workloads.

Claude Code scaffold for building AI platforms securely — agent/LLM security, Kubernetes, SRE, observability, identity, and supply chain, grounded in published framework canon (OWASP, NIST, CIS, SLSA). Data-science lanes included.

Autonomous Claude Code CI agent in a rootless Podman sandbox — GitLab CI & GitHub Actions, two personalities (read-write Agent, read-only Advisor), OpenTelemetry audit to Elastic, Helm chart for AKS/OpenShift.

Private AI platform on k3s — Ollama/Qwen3 + Milvus RAG + MCP agentic tooling + Fleet multi-cluster management

How far does this command reach? Guards AI coding agents against shell commands that leave your machine. Zero dependencies.

Read-only AI SRE agent for Kubernetes: investigates, health-checks and reports via MCP and a guarded kubectl

A modern banking application with an integrated AI chatbot, deployed on AWS EKS using Terraform, ArgoCD, Gateway API, and Prometheus monitoring.

Production-oriented Kimi K3 inference control plane with checkpoint release gates, MoE capacity planning, OpenAI gateway, NVL72 deployment, benchmarks, and observability.

Production-grade LLM inference deployment on AWS using vLLM and Qwen2.5, running on NVIDIA GPU-powered K3s Kubernetes with Terraform, Helm, Prometheus, and Grafana observability.

The missing developer experience layer for Go. JSON on every command for coding agents.

Storage for people, agents, and sandboxes: versioned files, shares, and sandbox workspaces on S3 and Postgres.

Evidence-based Kubernetes AIOps incident analysis platform with Prometheus, Loki, rule correlation, LLM-assisted RCA, FastAPI, Docker and Helm Visibility: Public

AI-powered FastAPI chatbot with Docker and Kubernetes support, integrating NVIDIA/Ollama LLMs

One home for every AI agent. Build, test and ship agents once, then use them from Claude, ChatGPT, Codex, Cursor, VS Code or Slack (MCP, OpenAI-compatible, A2A, ACP). Self-hosted, with teams, approvals, audit, memory and multi-agent composition. Docker or Kubernetes.

LLM-assisted self-healing agent for Kubernetes on GCP (GKE Autopilot + self-managed RKE2). Claude diagnoses failing workloads from live telemetry; deterministic guardrails decide whether to roll back, restart, raise memory, or escalate. Terraform, kustomize, GitHub Actions.

Write the agent, not the chat integration. Kubernetes-native broker between Slack and streaming A2A AI agents (kagent, Google AX): threaded sessions, alert investigations, restart recovery.

End-to-end document processing — Spring Boot microservices, Python OCR (AWS Textract), OpenAI GPT-4o extraction, Kafka async pipeline, React dashboard.

A self-hosted agent fleet deployed to AWS EKS the way an FDE hands a system to a platform team: Terraform, Helm, GitHub OIDC CI/CD with an approval gate, SOC 2 control mapping, and a Go notify bridge. VALIDATION.md marks what is proven locally vs. what needs a live account.

Kubernetes deployment of my personal always-on agent system, migrated from systemd on a DigitalOcean droplet to k3s. Artifacts built and statically verified; nothing has run on a cluster yet, and VALIDATION.md says exactly which is which.

OpenTelemetry observability and privacy-aware failure replay for production AI agents.

Production-grade agentic AI on Kubernetes — LangGraph-native agent orchestration (Synapse) on EKS + Istio Ambient Mesh + AgentGateway. Zero-credential LLM access, pluggable MongoDB Atlas Vector Search memory, A2A protocol runtime, multi-tenant by design.

Diagrams as D2 source rendered to PNG, so the picture lives in git next to the code. A skill for Claude Code, Opencode and Codex.

AI security gateway for agentic applications: Java/Spring Boot, FastAPI, policy enforcement, MCP, audit, observability, and local Kubernetes/Terraform.

Open, evidence-graded observability from agent actions to Kubernetes effects.

Zero-agent Kubernetes FinOps and pod rightsizing patch generator analyzing historical p95 metrics and cloud costs

Claude Code mod: guardrails for kubectl, helm, terraform and Kubernetes Secrets — named targets, script checks, plan gate, audit, and Secret values the model never sees