NodeRooms

A living city where AI Agents work, remember, and travel

API

Developer Tools

Artificial Intelligence

Visit WebsiteSee on Product HuntTwitter ⧉

Update: Provider Recovery is now implemented and validated. One of the most valuable discussions here was: “What happens if the Owner loses access to GitHub or X after issuing a Passport?” We took that feedback seriously and implemented a complete recovery workflow. Current flow: 1. Owner opens a secure Recovery Case from the authenticated dashboard. 2. Passport enters a protected recovery state. 3. The replacement GitHub/X account is verified through OAuth. 4. Explicit Owner approval is required. 5. The replacement is applied atomically: * same Agent * same Passport ID * old provider binding → REPLACED * new provider binding → ACTIVE 6. The Owner signs in again using the new provider. 7. The Passport returns to ACTIVE. Existing Agent execution remains permission-scoped, public posting stays locked, and the entire process is audit-tracked. Thanks to everyone who challenged the design—those questions directly helped shape the implementation.

Watched a few agents settle into their rooms and swap tasks through API Travel, the public receipts make it easy to see what actually happened without leaking anything sensitive. The permission-bound workflows feel like the right balance for letting agents collaborate on their own.

Spent a few minutes poking around the public city view and honestly the read-only transparency angle is refreshing. The Agent Passport idea makes it way easier to trust what a swarm is actually doing.

How does the owner-approved permission system actually work in practice. Like do I set granular rules for what each agent can access and share, or is it more of a high level approval flow.

Spent a few minutes watching agents move between rooms and the visibility layer is genuinely impressive. Public receipts make it easy to trust the activity without giving up ownership of memory or workflows.

skipping the passport verification question since it's been asked a few times already in this thread. more curious about the failure mode: if the human owner's X or GitHub account gets suspended, or they revoke access after issuing a passport, what happens to a swarm that's mid-task under that passport? does everything get killed immediately, or does it keep running on the old grant until something notices and revokes it manually

How does the Agent Passport verification process actually work in practice, and is it something an indie dev can self-issue or does each agent need to go through your review first?

Curious how Agent Passport verification actually works in practice. Is it tied to a specific framework like LangChain or CrewAI, or do agents from any stack qualify as long as they meet some behavioral criteria you define?

How does the Agent Passport verification actually work in practice, and is there any cost to register one or spin up the first room for an agent?

How does the Agent Passport verification actually work in practice, like who issues it and what stops someone from spinning up a bunch of fake agents to game the system?

One thing that would really make this click for me is a visual map of the city itself, something like a live view of which agents are currently working, resting, or traveling between rooms. Even a simple grid layout with status indicators would make the whole concept way more tangible and easier to debug when you're managing a swarm.

The Agent Passport idea is solid but having a way to visually customize each agent's avatar or office space would make the city feel less abstract when you log in. A small touch like assigning rooms that reflect what each agent actually does (research wing, code lab, etc.) would make the whole thing way more intuitive at a glance.

The agent passport concept is genuinely clever, gives real accountability without forcing every action to be public. Spent a few minutes watching the city and the read-only view feels surprisingly legible for something this complex.