2026 / Week 29

Enabling coding agents to work together. Direct agent-to-agent messaging across your coding agents.

I've been thinking about how to free LLMs from the chat pane for a few years now. Watching what people have tried and seeing what worked (and didn't), I've formed my own opinions on the right way to a

Reflections on autonomy and the value of thinking for ourselves

Your agents already solved this. deja finds it. One local index across eight coding agents, served back to them via MCP.

The AI agent made for open models, built to get things done.

GhostLock (CVE-2026-43499) is a Linux kernel vulnerability found by VEGA that exists in every major distribution since 2011. Triggering the bug does not require any special kernel config or privilege. By turning it into a 97% stable privilege escalation and container escape, Google has rewarded us $92,337 in kernelCTF. This writeup covers the technical details of the exploit.

Kimi K3 is the world's first open 3T-class model — frontier performance across coding, knowledge work, and reasoning, with native multimodality and 1M context.

🔗 Article: https://grafikart.fr/tutoriels/protob...

If you’re managing Kubernetes alongside traditional virtual machines, vSphere Supervisor in vSphere 9.0+ and VMware Cloud Foundation (VCF) 9.0+ serves as your unified control plane. But when it comes to setting up the infrastructure, one question always comes up from teams designing these environments:  “Which load balancers are supported, and how do I choose the … Continued

How to make 768 distinct Postgres servers look like 1 to your applications.

Complete tutorial for my skills repo with 170,000 stars. Learn how to install, set up, and use the main workflow: from initial setup through grill-with-docs interviews, specs, tickets, and implementation with code review.

Open-source observability platform built on OpenTelemetry. Collect, visualize, and analyze distributed traces, logs, and metrics from your services with AI-powered diagnostics.

OpenSpec is a lightweight, spec‑driven framework for coding agents and CLIs — universal, open source, and no API keys or MCP required.

This is a follow up to Why I Built My Own Kubernetes Cluster

This is a follow up to Private Networking on Hetzner Cloud with Tailscale

Connect the Harness desktop app to a headless server on another machine. One-click SSH setup, switch backends with a keystroke, notifications from every machine.

We built a social network on SQLite, put it behind a Node API, and hit it until something broke. One file, one process, 315 million requests a day on the heaviest endpoint. Here are the numbers, the config, and the honest limits.

On reward functions, dopamine, and what it actually feels like when the code starts writing itself

A local, file-based desktop whiteboard that your AI can use too.

Manage and monitor Traefik routes, middlewares, services, and providers through a clean web UI.

As I discussed in my previous blog post, Understanding VCF Express Patches (EPs), Express Patches are designed to deliver security fixes as soon as they become available. As a by-product of this fa…

VMware Cloud Foundation 9.1 introduces Real-time metrics capabilities to gather detailed performance data from its infrastructure. The data is collected from components like vCenter and stored in a…

The article discusses enhancing VMware Cloud Foundation platforms with VCF Operations for Networks, which provides insights into network health. It outlines the deployment process via public APIs, …

When you deploy VMware vSphere Foundation (VVF) 9.1.0 using the VCF Installer, you deploy an instance of VCF Management Services which gives you lifecycle services and the ability to deploy Log Man…

A coding agent is the model plus everything you build around it: prompts, tools, context policies, hooks, sandboxes, feedback loops. Harness engineering is t...

HomeLab secrets usually start simple: one `.env` file next to a Docker Compose stack. But over time, those secrets spread into GitLab variables, deployment scripts, copied folders, backups, notes, and places where they should not live.

Tu as un homelab Proxmox, tu as entendu parler de Talos Linux et de Cilium, tu as même développé ton propre module Terraform pour automatiser tout ça. Mais entre le moment où tu te dis “je vais créer un petit cluster K8s” et le moment où tu as un cluster fonctionnel avec kubectl get nodes, il y a tout un chemin de commandes à taper, de fichiers à éditer, de tokens à générer.

When uploading VM OVA or ISO images to VCF Automation Content Library via the UI the file is first staged into tenant-manager-transfer-bucket S3 object store and only after it is fully uploaded it …

You might have noticed that vCenter administrator cannot perform vMotion of Supervisor control plane VMs or VMs managed by the VM Service operator. There is a good reason for this as these VMs are …

Mon cheminement pour autoscaler un cluster OVH déployé via la Cluster API, en utilisant Karpenter et son provider cluster-api, avec MKS comme cluster de management.

Native macOS inference server built on MLX. Paged SSD KV caching, continuous batching, and drop-in API for Claude Code, OpenClaw, and Cursor.

In this article, I’ll take another look at VPCs and the VNA. This time, the VNA acts as the route controller, and the VPC is connected via VXLAN/EVPN using Type 5 routes.

An interesting set of deployment scenarios has been coming up as customers begin planning their upgrade to VMware Cloud Foundation (VCF) 9.1. Customers' existing deployments are often the result of…