n8n Labs launches open-source agent Nod: zero false memories in 216 injection attacks
Aiden_Tech_Ai · x · 2026-11-11
n8n Labs released Nod, an open-source personal agent that runs locally with its own browser to work across apps and websites — prepping calls, collecting invoices, canceling subscriptions — with any AI provider you choose.
Its key selling point is permission security: it only takes orders from you, emails or web pages it reads can't grant permission, and it checks before sending, paying, posting or deleting anything you didn't ask for. In 216 WhisperBench prompt-injection attacks, none planted a false memory.
Related event: n8n Open-Sources Personal Agent Nod with Strong Prompt-Injection Defenses(4 posts)→
More from coding & agent
- One-file playable stealth heist game built by Claude, all assets drawn in code — heypearlai · 2026-11-11
- Building an AI data analyst: how to handle conflicting per-user KPI definitions — Lopsided_Feedback_81 · 2026-11-11
- 7 memory slots vs 200K tokens: the hardware mismatch behind AI coding debt — esrtweet · 2026-11-11
- Sydney Codex Community Buildathon set for Nov 14 with Cerebras-backed ultrafast compute track — paw_lean · 2026-11-11
- shadcn's improve hits 10k stars: let top models plan, cheap models execute code fixes — shadcn · 2026-11-11
- OpenAI open-sources Codex Security CLI and SDK for AI-driven vulnerability scanning and fixing — openai · 2026-11-11