Derniers articles de la catégorie Agents IA

I Built a Custom Hermes Around Claude Code
Friday, August 28, 2026

Kanban, missions, tmux sessions, and metrics: how I built a customizable Agentic OS around Claude Code.

Securing Hermes on a VPS: My Three-Layer Audit
Friday, August 28, 2026

VPS exposure, permissions, scheduled jobs, and prompt injection: a verifiable method for keeping an autonomous agent under control.

My Agentic OS Goes Further Than Hermes
Thursday, August 27, 2026

How I built a customisable cockpit around Claude Code with Kanban, agents, skills, SQLite and headless/tmux runtimes.

Claude Code /design: Claude Design’s workflow comes to the CLI
Wednesday, August 19, 2026

A hands-on test of Claude Code’s /design command, its Artifact workflow, differences from Claude Design, and technical limits.

Agentic Engineering: What Really Separates It from Vibe Coding
Friday, August 14, 2026

The same setup and 100% AI-generated code can hide radically different practices. Here is how to separate Vibe Coding from Agentic Engineering.

Agentic stress testing: the loop does not stop at plan and execute
Wednesday, August 5, 2026

Your SaaS works for you. That says nothing about what happens with 200 concurrent users. The agentic workflow to load test with k6 and cross-check the result against production errors.

AI agent or n8n? My simple rule for choosing
Monday, July 27, 2026

Claude Code killed no-code and agents killed traditional automation. Yet I kept n8n. The real line is no longer no-code versus code: it is stochastic versus deterministic.

Hermes Agent: the practical guide (CLIs, skills, crons, kanban)
Saturday, July 25, 2026

VPS, CLIs, skills, kanban: the 4 layers of an AI agent that works 24/7. My crons, my content pipeline, and why CLIs matter more than skills.

There's no more craft in software development
Saturday, July 25, 2026

The dev job changed: you write decisions, not code. The real risk isn't AI, it's the atrophy of judgment. How to keep the ear that lets you steer.

ADRs: finally give your AI agents memory
Saturday, July 25, 2026

Your AI agent forgets everything each session. ADRs (Architecture Decision Records) and a context log give it a versioned, queryable memory.

Securing your SaaS with AI agents (lessons from a rogue pentest)
Saturday, July 25, 2026

AI makes pentesting trivial. Here are the 3 agents (prevent, fix, monitor) and the hardening rules to lock down your production SaaS.

One central brain for all my AI agents: Obsidian + Graphify
Wednesday, July 15, 2026

70× fewer tokens without changing models. An Obsidian vault plus a Graphify graph, shared by every agent I run. The full method.