Permission-Safety on Noureddine RAMDIhttps://ramdi.fr/tags/permission-safety/Recent content in Permission-Safety on Noureddine RAMDIHugoenSat, 23 May 2026 20:41:27 +0000Mercury Agent: A TypeScript AI assistant with persistent "Second Brain" memory and permission-hardened safetyhttps://ramdi.fr/github-stars/mercury-agent-a-typescript-ai-assistant-with-persistent-second-brain-memory-and-permission-hardened-safety/Sat, 25 Apr 2026 19:24:00 +0000https://ramdi.fr/github-stars/mercury-agent-a-typescript-ai-assistant-with-persistent-second-brain-memory-and-permission-hardened-safety/Mercury Agent is a TypeScript AI assistant with a persistent SQLite-based memory system, permission-hardened tools, and extensible skills, designed for safe, adaptive 24/7 operation via CLI or Telegram.