Agents API

Run Holo-powered computer-use agents that do work in a cloud browser or on a desktop: pre-built agents, custom agents, live sessions, skills, vaults.

A computer-use agent sees the screen and decides what to click, type, and scroll. Use it when the work lives behind a user interface with no API to call. The Agents API runs these agents for you: describe the work, and H provisions a browser or desktop, runs a Holo-powered agent that carries it out, and streams progress and the result back through a session your app can watch, steer, and stop. Everything below is available two ways: from the platform UI, where you build agents and launch sessions without writing code, and from the SDKs, CLI, and REST API.

Building blocks

Concept	What it is
Agent	A reusable configuration: environments, skills, model, and instructions. Reference a pre-built agent or create your own.
Environment	The surface the agent sees and acts on: a browser (cloud or local) or a local desktop.
Session	A single run of an agent against a task, with a lifecycle you can steer.
Skill	An optional, reusable instruction fragment the agent loads on demand.

See it in action

Ask for a specific vinyl on Amazon and the agent searches, opens the listing, and adds it to the cart, screenshot by screenshot.

From idea to production

Follow the lifecycle or jump to what you need.