Networking AI Agents on Kubernetes (2): Local LLM InferenceRunning inference locally in Kubernetes is harder than deploying any other workload. GPU resource model, model storage, and scaling all require different thinking.
Networking AI Agents on Kubernetes (1)AI agents invert the usual traffic model: their traffic is mostly outbound, long-lived, and body-driven. Standard Kubernetes networking primitives don't handle this well.
The Next Programming Language: Formalized HumanSoftware engineers have always used formal languages. As we shift to communicating with AI coding agents, we're ascending to a new level—human language with professional formality, like law or medicine.
Restricted Execution for LLM Agents: Sandboxing Untrusted CodeExploring sandboxing techniques for safely executing LLM-generated code using firejail, sandbox-exec, and go-restricted-runner
Link: EpsilonA zero-dependency WASM runtime written in Go
Kagent: Declarative Kubernetes Resources for Multi-Agent AI SystemsExploring Kagent, a CNCF sandbox project that brings cloud-native principles to AI agent orchestration using Kubernetes Custom Resource Definitions
Bridging the Gap: Empowering LLMs with Secure Command-Line AccessLarge Language Models (LLMs) are transforming how we interact with technology, offering incredible potential for automation and assistance. However, one of t...
API GatewaysAn API Gateway is the front door to your applications, sitting between users and backend services. It handles authentication, rate limiting, load balancing, and more.
Link: Stop deploying Web Application Firewalls (WAFs)Stop deploying web application firewalls
Anatomy of an ingress controller based on EnvoyAdobe's ingress controller is built on top of Envoy, which acts as a **data plane** that routes requests. A **control plane** creates a valid configuration f...
Link: why HTTP-3 is eating the worldWhy HTTP/3 is eating the world | APNIC Blog
Link: Load BalancingA nice graphical representation of how a Load Balancer works.
Link: Kubernetes Apply vs. Replace vs. PatchKubernetes Apply vs. Replace vs. Patch
Link: Kubernetes Controllers at Scale> “*Whether you are already working on some Kubernetes project or are just getting started with developing your first Kubernetes Operator, chances are high t...
Link: System design and the cost of architectural complexitySystem design and the cost of architectural complexity