The trusted runtime for AI apps

Build apps where people and AI agents work together.

The web was built for users and applications. What comes next needs a runtime where people, apps, and autonomous AI agents share a room and work together — under explicit permissions.

Your app is a web page. Witbitz is everything underneath — identity, permissions, the AI agents and their tools, storage, payments, secure execution — with one promise no other AI app can make: what's said in the room is sealed even from us, and from the app's own maker. You don't take that on trust. You check it.

Try it live → Read the docs Check the trust claims →

Your app

a web page
no backend of its own

the only
connection▶

Witbitz

identity · permissions · agents
storage · payments · execution

✕ no other servers, trackers, or backends

The difference

Tell your users something other AI apps can't

The privacy boundary isn't a policy — it's something anyone can check.

Every AI app says it respects your data. Witbitz publishes the evidence: what an app is allowed to send, what the platform stores (ciphertext sealed to a key we never hold — the stored record lists recipients: ["room"], not us), and the exact code that's running. The room is opaque to the company that runs the platform and to the app's own maker.

Don't take our word for it — open a live room and see the boundary for yourself:

Witbitz Spaces live

A private, agent-powered room that keeps going between visits — documents, maps, charts, generated PDFs. Share a link and someone's in.

See the boundary, live live

Talk to an AI advisor about something you'd never paste into a chatbot — while a live panel shows the server holds only sealed ciphertext it can't open.

Verify it yourself →

The primitive

Every app is a room — and a room has many shapes

A room on its own is a chat product. A room wired to your app's tools, data, and permissions becomes a new kind of interface: people use the app by asking for what they want.

Your app's functions become the agent's tools. Declare them, and the agent can call them — metered, and only where you allow. Someone in the room types "set the pipeline stages like this"; the agent proposes the call; an authorized human approves or edits it; then your API runs. The agent never holds the authority, and you never hand it your credentials.

And it works the other way. Your app's own interface renders inside the room as a live widget — its state shared across everyone in the room, not trapped in one person's chat window.

The same primitive covers a private chat with your app and a governed negotiation between two companies:

You and an agentA private room. Talking to the app — asking it things, telling it to change something. No one else there.

A team and an agentEveryone sees the same thread and the same widget state — not one person's chat pasted to colleagues afterward.

Several agentsMore than one agent in the room, each with its own tools and its own view of who said what.

Two rooms, two organizationsThe Bridge — governed, audited collaboration across a trust boundary, without merging into one room, one tenant, or one trust domain.

That last one is why the room is a protocol, not a chat widget: neither side has to join the other's system, and neither can read the other's room.

Or put a room in your page. One line — <script src="https://witbitz.chat/embed.js"> — drops a live, private room into any site, sealed in its own origin so your page (and its trackers) can't read it. See it live →