Derniers articles de la catégorie Agents IA
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.
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.
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.
Your AI agent forgets everything each session. ADRs (Architecture Decision Records) and a context log give it a versioned, queryable memory.
AI makes pentesting trivial. Here are the 3 agents (prevent, fix, monitor) and the hardening rules to lock down your production SaaS.
70× fewer tokens without changing models. An Obsidian vault plus a Graphify graph, shared by every agent I run. The full method.
Boris Cherny, the creator of Claude Code at Anthropic, just shared a repo that exploded on GitHub. Inside: the most comprehensive recap of the paradigm shift we've been living for 6 months.
Switching from OpenClaw to Hermes Agent: step-by-step VPS install, security, classic gotchas and first useful cron. The complete guide.
Anthropic just shipped Opus 4.8 and Dynamic Workflows: one prompt is enough to launch up to 1000 parallel agents. The proof: Bun migrated from Zig to Rust in 11 days, 750,000 lines, 99.8% tests passing.
Starting June 15, 2026, Anthropic moves Claude Code's programmatic mode to the API pool. How to keep automating Claude on your Max subscription with node-pty and tmux.
Anthropic presents programmatic credits as a bonus. For developers building harnesses around Claude Code, it feels more like a change in the contract.
Markdown is still excellent for feeding AI, but HTML is becoming more powerful for some human-facing agent outputs.