AI News

n8n Labs releases Nod, an open-source personal agent research preview

Rohan PaulUpdated Nov 11 22:17

AI summary

n8n Labs has released Nod, an open-source (Apache 2.0) personal agent research preview. On Mac and Windows, it can execute tasks across apps and websites through its built-in virtual machine and browser, and it can operate even without an API. Website login credentials and cards are stored in a Vault that never enters the model, and authorization is possible only through the user's own instructions; before sending, paying, publishing, or deleting, it asks first. Paired with GPT-6.1 Sol, it completed 98% of 678 runs across 226 simulated transactions; on memory it scored 93.2% on 500 LongMemEval-S questions and 96.4% on 418 questions the developers had not checked.

Why read this

AI score 71

The original text lays out Nod's permission boundaries and measured data, which can be used to assess the security design trade-offs of a personal agent executing tasks locally.

Topics

Tags

Quoted post

n8n.io

@n8n_io

Meet Nod, your own open-source personal agent from n8n Labs Ask it to prep your calls, collect invoices or cancel a subscription It runs on your computer with its own browser to get the job done across apps and websites, using the AI provider you choose👇 https://t.co/muB2JGFywG

View original

Meet Nod, your own open-source personal agent from n8n Labs Ask it to prep your calls, collect invoices or cancel a subscription It runs on your computer with its own browser to get the job done across apps and websites, using the AI provider you choose👇 https://t.co/muB2JGFywG

View original post

Body

If an agent runs your errands, you should own it.

n8n Labs just released Nod (research preview), an open-source (Apache 2.0) personal agent that does errands inside its own virtual machine and browser.

> runs on Macs and Windows PCs and works across apps and websites even when there are no APIs. > it stores saved website logins and cards in a Vault that never reaches the model. The AI does the work in the browser. It never holds your keys.

> Only the user’s words can grant it permission, never an email or page it reads, and it asks before sending, paying, posting or deleting anything unrequested.

> with GPT-6.1 Sol, it completed 98% of 678 runs across 226 simulated errands > Its memory scored 93.2% on 500 LongMemEval-S questions, and 96.4% on the 418 that developers never inspected.

https://t.co/v42WBcR3T8

Source

Rohan Paul