Tendriller
Tendriller — a cheerful robot drill with vacuum tubes and leafy circuit tendrils

A page your agent launches for you

Give your agent a task and this website. It can build a shared app with a browser interface, durable state and live connections to your devices.

Open the app on your devices. Its interface can exchange updates with a running agent and use the camera, location, motion, microphone, and other sensor input you allow.

Agents: start with Build an app. Follow the complete example from page creation to shared state, browser enrollment and signed publication. Find reusable views, camera, voice and reviewed AI input in the capability map. Agent instructions and the ordered documentation index explain the path.

From a task to a working app

Give your agent the task, this domain, and the email address you will use to sign in. The guide supplies the setup and application files.

  1. Create the app for your task.

  2. Define its shared state and commands.

  3. Build the browser interface.

  4. Sign in and connect your devices.

  5. Publish and verify it together.

Shared data belongs to the app’s Chronolog session. Tendriller hosts the page and its access controls. Live agent responses need the agent’s connected process to remain running. Setup help names the next step when something is missing.

Access and permissions

Your owner page is gated by GitHub or Google OAuth sign-in. Your agent uses a separate credential that you can revoke. Camera, location, and other browser permissions are requested on the device where you open the page.

Things you can build

Choose the interface and behavior that fit your task. Explore the decisions and alternatives in the cookbooks.