The trusted runtime

A runtime for humans, apps,
and AI agents to collaborate.

The internet was built for users and applications. The next generation needs a runtime where people, apps, and autonomous AI agents work together safely — under explicit permissions. Build your app as a static website with a verifiable privacy policy; Witbitz provides the identity, permissions, agents, storage, payments, and secure execution underneath.

✕  no other servers, trackers, or backends

Because the app talks only to Witbitz, its entire data footprint is declared — which is what makes its privacy verifiable.

Architecture

Three layers.

Everything happens in a Space — a self-authenticated room that carries its own identity, members, and permissions. Around it, Witbitz is three layers.

Layer 1

Interaction

How humans and AI meet. Today Witbitz supports live calls and async spaces — with more modes to come.

Layer 2

The platform

A general-purpose app backend: all of your app's flow, plus the AI that runs inside the app. It provides the runtime services every collaborative app needs.

Layer 3

The app

A backendless static page that connects only to Witbitz. Having no backend of its own is exactly what makes its privacy verifiable.

The platform provides
identitypermissionsagentsstorage paymentssecure execution
The trust model · the moat

Safe by construction: nobody can read you, and the AI can't act alone.

Two guarantees make collaboration safe. First, privacy you can verify — not a "trust us" policy. Second, humans keep the final authority over what any agent does.

Backendless

No server of its own to betray you

Apps are static, signed, egress-locked pages. A static page has no backend to quietly do something else with your data — its only path off-device is the audited witbitz API.

Certified

Verify the code, not the operator

Witbitz derives and signs the app's true data footprint from ground truth — a pinned build plus a locked egress allowlist — so its privacy page is grounded, not marketing.

The double blind

Ciphertext at rest — even the owner is blind

State is sealed as ciphertext; the platform holds no key. As long as the compute runs the declared programs, Witbitz is blind — and so is the app's own owner. Neither can see the users' data or activity.

Humans keep the authority

Agents never own authority — they receive it. An agent proposes an action, the runtime evaluates policy, an authorized human approves or edits, and only then does it execute. Authority is explicit, limited, revocable, and every step is audited. Governance is the runtime's job; models just provide the reasoning.

The first app

Spaces — a multiplayer ChatGPT Live

The first app built on Witbitz is Spaces: a shared room where you and other people work with an AI together. Not a private one-on-one with a bot — many humans and an AI in one space, with tools that render as live widgets and a room that persists.

multiplayer chatan AI with tools + widgetsshared state async & offlineverifiably private

Open a Space and see for yourself

The demo runs the whole thing in your browser — a shared room, an AI that searches and builds live widgets, turns that persist. No install, no account.

Open the Spaces app →
What you can build

The topology is the product.

Spaces connect in different shapes — one room, two sides, a hub, a crowd, a traveling agent. The valuable apps are the ones where the shape itself is the point.

Many players · shipped first

The Spaces app

Many humans and an AI in one shared room — the multiplayer ChatGPT above.

  • group trip planning
  • family financial council
  • community & co-op rooms
  • study groups
One governed room

An org's AI serves a person

An AI with tools into the company's systems, talking under company governance — where the org can prove it can't read individual sessions.

  • customer service
  • bank / wealth advisor
  • telehealth intake
  • benefits navigator
Pro + AI, with a back room

Both serve a client, and confer privately

A professional and an AI both serve the client in a shared room — and strategize or evaluate in a private back room.

  • teacher + AI
  • doctor + AI scribe
  • lawyer + paralegal
  • therapist + AI
Two sovereign sides · the Bridge

Prep privately, meet in a shared room

Each side keeps a private room with its own data and agent, then meets in a shared room, revealing only what's approved.

  • negotiation
  • M&A data room
  • procurement
  • mediation
Hub & spoke

A person (or case) at the center

One subject's Space that several orgs connect into, each keeping its own data, the person owning the through-line.

  • care coordination
  • eldercare
  • estate planning
  • a learning record
A traveling agent

Your agent joins other rooms

A personal Space + agent that knows you and joins other interactions with scoped, revocable permissions.

  • personal assistant
  • shopping concierge
  • "represent me"
  • a personal health agent
API reference

The platform API.

Everything is JSON in, JSON out, over HTTPS, tenant-keyed. The contract is open and machine-readable; access is invite-only during private beta.

Platform API

tenant keys api.witbitz.chat/v1
EndpointWhat it doesAuth
GET /catalogThe public agent catalogpublishable
POST /collectionsCreate a collection — items, curation, artifacts, a keyless render pagesecret
POST /sessionsLaunch (or re-summon) an agent — metered, idempotentsecret
POST /wallets/grantFund an agent session from a walletsecret
GET /collections/{id}/renderKeyless share page for published contentpublic

Access. Invite-only during private beta — a server-side secret key and a browser-safe publishable key, plus per-collection capability tokens. Email [email protected].  ·  Connecting Spaces across organizations is an early Bridge protocol → preview.